© 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-2-9B
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105216
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    tonode
    -0.98
    oredCriteria
    -0.69
    antMatchers
    -0.53
    uxxxx
    -0.47
    runApp
    -0.44
    styleType
    -0.40
    AndFlush
    -0.38
     quirúrg
    -0.37
    tagext
    -0.37
     Rodin
    -0.36
    POSITIVE LOGITS
    MigrationBuilder
    3.69
    KURZBESCHREIBUNG
    1.73
    WriteBarrier
    1.66
     '\\;'
    1.11
    تقاوى
    1.03
    ($__
    0.90
     esboço
    0.89
    woff
    0.83
     صوتيه
    0.82
    SPATH
    0.81
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.