© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 2301
    Prev
    Next
    INDEX
    Explanations

    locations and references to illegal drug trafficking activities

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

    places and technical terms

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     from
    -2.27
    from
    -1.87
     FROM
    -1.58
    From
    -1.54
     From
    -1.51
    从
    -1.50
     từ
    -1.48
     dari
    -1.47
     från
    -1.46
    จาก
    -1.44
    POSITIVE LOGITS
     ModelExpression
    0.71
     into
    0.59
     onto
    0.58
     AssemblyTitle
    0.54
    Into
    0.53
     OFDb
    0.52
    ESTAMP
    0.50
     समीक्षक
    0.50
    Tembelea
    0.50
    aarrggbb
    0.50
    Activations Density 0.358%

    No Known Activations