© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 15338
    Prev
    Next
    INDEX
    Explanations

    references to toxicological evaluations and safety assessments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Toxicity or safety information

    np_acts-logits-general · gemini-2.0-flash

    acute and chronic toxicity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     campers
    -0.68
    BorderFactory
    -0.66
    IntoConstraints
    -0.65
    ghed
    -0.62
     GridLayout
    -0.61
     dancers
    -0.61
    帖最后由
    -0.60
     Batal
    -0.60
    stateProvider
    -0.59
    UAV
    -0.59
    POSITIVE LOGITS
     toxicity
    0.87
     toxicological
    0.76
     toxicology
    0.73
     exposure
    0.70
    toxicity
    0.68
     Exposure
    0.65
     Toxicity
    0.64
     exposures
    0.62
     toxic
    0.61
    Exposure
    0.60
    Activations Density 0.712%

    No Known Activations