© 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 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. 14963
    Prev
    Next
    INDEX
    Explanations

    elements related to medical research and experimental methodologies

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

    HTML tags

    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
    Jîn
    -0.69
     समीक्षाएं
    -0.66
     Italijanski
    -0.63
     GenerationType
    -0.59
     disambiguazione
    -0.58
    المشاركات
    -0.58
    InputBorder
    -0.58
     Taktlose
    -0.57
    Erreferent
    -0.57
    RTLI
    -0.57
    POSITIVE LOGITS
    ↵↵
    1.21
    <h2>
    0.86
    <h3>
    0.84
    <h4>
    0.70
    <h1>
    0.67
    <strong>
    0.56
    <h5>
    0.50
    <h6>
    0.44
    ↵↵↵
    0.44
    <em>
    0.40
    Activations Density 0.002%

    No Known Activations