© 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. 101036
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and jargon related to data structures and programming

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

    Programming and technical language tokens that indicate data types, comparison operations, XML tags, and domain-specific technical terms.

    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
    MigrationBuilder
    -0.51
    पया
    -0.50
    reportWebVitals
    -0.48
     ſche
    -0.47
     indígen
    -0.47
    RTLU
    -0.46
     FetchType
    -0.45
    zelfde
    -0.45
     queſta
    -0.44
    yntaxException
    -0.43
    POSITIVE LOGITS
    IndentedString
    0.49
    Kanpo
    0.42
     dead
    0.41
    /*++
    0.41
    UrlResolution
    0.40
     lagi
    0.40
    الدراسه
    0.40
     PagesJaunes
    0.40
     Pingback
    0.39
     '\\;'
    0.38
    Activations Density 0.072%

    No Known Activations