© 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. 13883
    Prev
    Next
    INDEX
    Explanations

    relationships and interactions in research studies

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

    limited evidence and specific studies

    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
     TWICE
    -0.46
     twice
    -0.46
     ویکی‌پدیای
    -0.42
     مشارکت‌کنندگان
    -0.42
     Twice
    -0.42
    bli
    -0.42
    май
    -0.41
     Bask
    -0.41
    KeyValuePair
    -0.41
    twice
    -0.41
    POSITIVE LOGITS
     siquiera
    0.71
     réellement
    0.70
     proprement
    0.69
     egent
    0.65
     específicamente
    0.63
     précisément
    0.61
     eigentlichen
    0.60
     verdaderas
    0.59
     specifically
    0.58
     vraiment
    0.58
    Activations Density 0.446%

    No Known Activations