© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 104377
    Prev
    Next
    INDEX
    Explanations

    special characters and punctuation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Punctuation or connecting symbols that separate elements in structured text, including periods, equals signs, multiplication symbols, and descriptive connectors in scientific, programming, or mathematical contexts.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered 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
    Not in Any Lists

    No Comments

    Negative Logits
     שוליים
    -0.75
    SourceChecksum
    -0.72
     surla
    -0.69
     autorytatywna
    -0.67
     Мексичка
    -0.66
    tvguidetime
    -0.65
    uxxxx
    -0.65
    %"),
    -0.65
    Hochspringen
    -0.64
    httphttps
    -0.64
    POSITIVE LOGITS
    web
    0.34
     Rie
    0.34
    OK
    0.33
    しと
    0.33
    ティス
    0.32
    le
    0.31
     di
    0.31
    se
    0.30
     Würzburg
    0.30
     him
    0.30
    Activations Density 0.089%

    No Known Activations