Content safety evaluation
Evaluate the safety of prompt input and output responses against a set of defined safety policies.
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.
Explore 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.
Slide 1 of 2
Capabilities
Tuneable, open models
ShieldGemma models are provided with open weights and can be fine-tuned for your specific use case.
Model variants
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.
Download ShieldGemma 2
Hugging Face
