© 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. 104932
    Prev
    Next
    INDEX
    Explanations

    keywords and terms related to coding and programming structures

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

    Special tokens that appear in structured text formats like code, markup, or data schema, often serving as identifiers, property names, or structural elements in programming contexts.

    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
    expandindo
    -0.79
     betweenstory
    -0.68
     Мексичка
    -0.65
    adpleegd
    -0.61
    parsedMessage
    -0.57
    featureID
    -0.56
    InputBorder
    -0.55
     lenker
    -0.55
    forChild
    -0.53
    تقاوى
    -0.52
    POSITIVE LOGITS
    tional
    0.39
    それだけ
    0.38
     White
    0.37
    QG
    0.34
    ID
    0.34
     seconds
    0.34
     ID
    0.34
     pati
    0.33
    ler
    0.33
    sec
    0.33
    Activations Density 0.002%

    No Known Activations