{"id":"shieldgemma","name":"ShieldGemma","maker":"Google","url":"https://ai.google.dev/gemma/docs/shieldgemma","summary":"Open-weight Google safety classifiers built on Gemma that check text prompts, responses and images against safety policies.","details":"ShieldGemma 1 comes in 2B, 9B and 27B sizes for text, and ShieldGemma 2 is a 4B model for labelling images. Weights are on Hugging Face and Kaggle under Gemma terms, which are not an open-source licence, and can be fine-tuned.","open_source":false,"hosted":false,"verified":"2026-11-15","category":"safety","category_name":"Guardrails and security","page":"https://modelmoot.com/tools/shieldgemma","reviewed":"2026-11-15","checked":{"at":"2026-11-15T16:10:15.342Z","address_answers":true},"note":"Descriptions are the site's own. Facts under \"checked\" were read automatically from the tool's address and public repository."}