© 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. 112713
    Prev
    Next
    INDEX
    Explanations

    concerns and risks related to security and privacy

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     frust
    -0.40
     للتو
    -0.40
     application
    -0.38
    phosphat
    -0.38
    AnchorStyles
    -0.37
    좌
    -0.37
     bás
    -0.36
     responsiveness
    -0.36
     interfer
    -0.35
    調子
    -0.35
    POSITIVE LOGITS
     riesgo
    0.59
     peligro
    0.58
     NSCoder
    0.58
     rischio
    0.57
     risk
    0.57
     riesgos
    0.57
     dangers
    0.56
    dangerous
    0.55
    Risk
    0.55
     risks
    0.55
    Activations Density 0.045%

    No Known Activations