© 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. 20103
    Prev
    Next
    INDEX
    Explanations

    symbols and punctuation marks in the text

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

    numbers like 8

    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
    Frankreich
    -0.32
    んご
    -0.31
    extField
    -0.31
     Bonaparte
    -0.30
    Vanjske
    -0.30
    enterian
    -0.30
     않습니다
    -0.29
     Hombre
    -0.29
     CommandType
    -0.29
     EconPapers
    -0.29
    POSITIVE LOGITS
    8
    0.84
     Eight
    0.69
    TagMode
    0.68
     eighth
    0.66
     wireType
    0.66
     Ocho
    0.65
    centiles
    0.65
     EIGHT
    0.63
     eight
    0.62
     VIII
    0.62
    Activations Density 0.198%

    No Known Activations