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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 33079
    Prev
    Next
    INDEX
    Explanations

    concerns related to health and safety risks

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

    risk and safety

    np_acts-logits-general · gemini-2.5-flash-lite

    mentions of danger, risk, or threats to safety, health, or critical infrastructure.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0

    references to dangers or threats—especially safety hazards, injuries, public health risks, crime/security concerns, and risks to critical infrastructure or utilities.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    CodedInputStream
    -0.54
    postIndex
    -0.52
    parsedMessage
    -0.51
     initComponents
    -0.50
    ynomial
    -0.48
    /*
    -0.47
    setVerticalGroup
    -0.47
    |}{$
    -0.47
     للاسماء
    -0.47
    phyllum
    -0.46
    POSITIVE LOGITS
     unsafe
    0.52
     safety
    0.50
     dangerous
    0.48
     peligroso
    0.46
     dangerously
    0.45
    safety
    0.43
     risk
    0.42
     risking
    0.42
     dangereux
    0.42
     seguridad
    0.41
    Activations Density 0.054%

    No Known Activations