© 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. 31-GEMMASCOPE-RES-131K
    11. 46714
    Prev
    Next
    INDEX
    Explanations

    occurrences and variations of the word "punch," reflecting contexts related to striking or hitting

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

    punch and variations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EnglishChoose
    -0.39
    resave
    -0.32
    存于互联网档案馆
    -0.31
     Scotia
    -0.31
     Metropolitana
    -0.31
     Rector
    -0.30
    medad
    -0.29
     assoluto
    -0.29
     Mariana
    -0.28
     Settings
    -0.28
    POSITIVE LOGITS
     punch
    1.23
    Punch
    1.21
    punch
    1.20
     Punch
    1.15
     PUNCH
    1.09
     punches
    0.99
     punching
    0.99
     punched
    0.95
     holes
    0.72
    holes
    0.66
    Activations Density 0.004%

    No Known Activations