© 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. 3743
    Prev
    Next
    INDEX
    Explanations

    email addresses

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

    URLs and foreign language text

    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
    .,
    -0.64
    .
    -0.63
    дравствуйте
    -0.61
     Vries
    -0.52
    ,
    -0.50
    <strong>
    -0.50
     Moines
    -0.48
     piłkarz
    -0.48
    (
    -0.47
     zetten
    -0.46
    POSITIVE LOGITS
    withstanding
    1.00
     كومونز
    0.91
    intios
    0.89
     ostavi
    0.77
     betweenstory
    0.76
    contentLoaded
    0.74
     disambiguazione
    0.74
    PerformLayout
    0.73
    MigrationBuilder
    0.73
    脚注の使い方
    0.73
    Activations Density 0.172%

    No Known Activations