© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 72290
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate precedence or uniqueness in programs or studies

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

    of its kind

    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
     ExecuteAsync
    -0.48
    IsMutable
    -0.46
     للاسماء
    -0.43
    MigrationBuilder
    -0.42
    Koordinaten
    -0.42
    NewUrlParser
    -0.40
     beginnetje
    -0.39
     Wikiseite
    -0.39
    OwnProperty
    -0.38
     afhankelijk
    -0.38
    POSITIVE LOGITS
     its
    1.05
    its
    0.77
     kind
    0.75
    Its
    0.71
    其
    0.69
     Its
    0.68
     svého
    0.66
    kind
    0.65
    Kind
    0.63
     KIND
    0.63
    Activations Density 0.031%

    No Known Activations