Google DeepMind
Try Google AI Studio Try Gemini

ShieldGemma 2

Gemma

A collection of lightweight, state-of-the-art open models built from the same technology that powers our Gemini models

Try in Google AI Studio

Our most advanced open models help developers create AI applications that run wherever users need them — from workstations to laptops and even phones.

Model family

Performance and benchmarks

Official variants

We’re exploring applications for Gemma as a code generator, in healthcare support roles, and even as a research tool in the animal kingdom.

View all models

MedGemma

A Gemma 3 variant optimized for medical text and image comprehension.

Learn more

ShieldGemma 2

A suite of safety content classifier models built on Gemma 2 and designed to detect harmful content in AI models’ text inputs and outputs.

Learn more

PaliGemma 2

A family of lightweight, open, vision-language models that can interpret text and image inputs.

Learn more

DataGemma

Fine-tuned Gemma 2 models that integrate retrieval techniques to ground responses in real-world data.

Learn more

Gemma Scope

A set of interpretability tools built to help researchers understand the inner workings of Gemma 2.

Learn more

CodeGemma

A collection of powerful, lightweight models that can perform a variety of coding tasks.

Learn more

Gemma (APS)

A research tool that uses abstractive proposition segmentation (APS) to break down complex text into meaningful components.

Learn more

TxGemma

A collection of open models designed to improve the efficiency of therapeutic development.

Learn more

RecurrentGemma

A family of open models using a novel recurrent architecture for faster processing of long sequences.

Learn more

Start building with Gemma

Supported by popular frameworks and platforms.

Hugging Face Transformers

Keras

Ollama

PyTorch

Gemma.cpp

JAX

MediaPipe

Google Cloud

Gemma Cookbook

A GitHub repository, collecting quickstart guides and code examples.

View cookbook

Developer events

Revisit past Developer Days, I/O sessions and other events where we’ve shared updates, and highlighted new opportunities for developers using our open models.

Building intelligent agents with Gemma 3

Explore the development of intelligent agents using Gemma models, with core components that facilitate agent creation, including capabilities for function calling, planning, and reasoning.

Gemma 3 architecture and design

Discover how with Gemma 3, we have tried to push many of the limits of what makes a model usable and practical.

Welcome to Gemma 3

Discover the latest advancements in Gemma, Google's family of lightweight, state-of-the-art open models.

Deepdive into Gemma 3

Hear how the Gemma research team unveil the architecture, design principles, and innovations behind Google's family of lightweight, state-of-the-art open models.

A truly multilingual Gemma 3

Building multilingual AI applications is crucial for reaching global audiences, and varied language proficiency remains a top developer priority.

Explore the Gemmaverse

A vast ecosystem of community-created Gemma models and tools, ready to spark imagination and power innovation.

Start exploring
ShieldGemma 2

ShieldGemma 2

A suite of safety content classifier models built on Gemma 2 and designed to detect harmful content in AI models’ text inputs and outputs

Read blog

Download ShieldGemma 2

Instruction-tuned models for evaluating the safety of text and images against pre-defined safety policies. Helps evaluate and prevent generative AI applications from violating safety policies.

Watch

Model versions

  • ShieldGemma 1

    Built on Gemma 2 and available in 2B, 9B, and 27B parameter sizes.

  • ShieldGemma 2

    A 4B parameter image safety model built on Gemma 3.

Capabilities

  • Content safety evaluation

    Evaluate the safety of prompt input and output responses against a set of defined safety policies.

  • Tuneable, open models

    ShieldGemma models are provided with open weights and can be fine-tuned for your specific use case.

Watch