© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 69953
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuations used in formal referencing and citation

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

    specific names and entities

    np_acts-logits-general · gemini-2.5-flash-lite

    structural markers of formal listings and citations—function words and punctuation that introduce roles, case names, quoted definitions, or italicized titles.

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    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
     vectorielles
    -0.39
     bénévoles
    -0.33
     nemlig
    -0.32
     étoit
    -0.31
    ‍
    -0.31
     ouvrages
    -0.30
     gantung
    -0.30
     financières
    -0.30
     eſt
    -0.29
     viñ
    -0.29
    POSITIVE LOGITS
    endphp
    0.85
     kasarigan
    0.84
     Administrativna
    0.82
    ValueStyle
    0.80
    __(/*!
    0.75
    Hentet
    0.72
    ❋
    0.71
     تضيفلها
    0.69
    Архівовано
    0.66
    angliski
    0.66
    Activations Density 0.008%

    No Known Activations