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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 91261
    Prev
    Next
    INDEX
    Explanations

    various uses of punctuation marks and symbols in code or formatting

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

    punctuation and separators

    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
    ècie
    -0.60
    matchCondition
    -0.54
    enterOuterAlt
    -0.50
    
    -0.50
    KommentareTeilen
    -0.48
    msgTypes
    -0.47
    EndProject
    -0.47
    Хро
    -0.45
    //
    -0.44
     discre
    -0.43
    POSITIVE LOGITS
    Personendaten
    0.37
     vedi
    0.36
     anchorage
    0.36
     Consulte
    0.36
     relief
    0.34
     îng
    0.34
     capitales
    0.33
     dessas
    0.33
    foria
    0.33
    WritableDatabase
    0.33
    Activations Density 0.005%

    No Known Activations