© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 3919
    Prev
    Next
    INDEX
    Explanations

    legal terminology and references to coroner proceedings

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    higher fraction

    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
    Negative Logits
     clés
    -0.50
     olho
    -0.47
     lauk
    -0.46
     econô
    -0.45
     strategia
    -0.45
    CommandLine
    -0.45
     Geist
    -0.45
     remota
    -0.44
     stratégies
    -0.44
     nocturne
    -0.43
    POSITIVE LOGITS
     مشين
    0.83
    istoitu
    0.68
     HttpNotFound
    0.68
    icose
    0.64
    StoreMessageInfo
    0.63
     ModelExpression
    0.62
    Abitanti
    0.60
    BufferException
    0.60
    astéroïdes
    0.59
    ochlor
    0.58
    Activations Density 0.014%

    No Known Activations