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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 82254
    Prev
    Next
    INDEX
    Explanations

    modal verbs, specifically variations of "can" and "cannot," indicating ability or possibility

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

    can followed by verb

    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
    ситет
    -0.32
     can
    -0.30
     essay
    -0.30
    seende
    -0.28
    今度は
    -0.28
    inske
    -0.27
    ěry
    -0.27
    NewLabel
    -0.27
     tarko
    -0.27
    зя
    -0.27
    POSITIVE LOGITS
    oredCriteria
    0.80
    httphttps
    0.75
     ProtoMessage
    0.67
     nahilalakip
    0.66
    outWeight
    0.65
    principalColumn
    0.65
     otomatig
    0.64
     AssemblyTitle
    0.63
    帖最后由
    0.61
     sumpay
    0.59
    Activations Density 0.017%

    No Known Activations