© 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. 105356
    Prev
    Next
    INDEX
    Explanations

    elements related to geographical locations and countries

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

    Country names followed by whitespace in tabular or structured data formats, particularly in scientific or technical documents.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219
    Triggered by @lu-christina
    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
    Negative Logits
    ThroughAttribute
    -0.57
    WindowConstants
    -0.54
    RefreshLayout
    -0.50
    transQ
    -0.49
     ""],
    -0.48
    nestjs
    -0.47
    ChildScrollView
    -0.45
    mergeFrom
    -0.45
    posedge
    -0.44
    ureusement
    -0.44
    POSITIVE LOGITS
     resourceCulture
    0.45
     Administrativna
    0.35
    LookAnd
    0.33
    Ste
    0.33
    bufio
    0.33
     Италијани
    0.32
     Ste
    0.32
    istics
    0.32
     pää
    0.32
    IORS
    0.32
    Activations Density 0.243%

    No Known Activations