© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 110718
    Prev
    Next
    INDEX
    Explanations

    indicators of safety and cytotoxicity in biological studies

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

    skin and eye irritants

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pushFollow
    -0.66
     NSCoder
    -0.62
     defStyle
    -0.56
    zzleHttp
    -0.55
    EReference
    -0.52
    DeleteBehavior
    -0.51
     HasFactory
    -0.50
    routeProvider
    -0.50
    adaptiveStyles
    -0.50
     VizieR
    -0.49
    POSITIVE LOGITS
    irritation
    0.59
     Irrit
    0.58
     skin
    0.57
     irrit
    0.54
    Irrit
    0.54
    Skin
    0.54
     irritate
    0.54
     irritant
    0.53
     irritation
    0.53
    skin
    0.53
    Activations Density 0.001%

    No Known Activations