Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 120850
    Prev
    Next
    INDEX
    Explanations

    specific technical and scientific terminology related to composition, structure, and professional applications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.64
    IVEREF
    -0.63
    +#+#
    -0.63
    +#+
    -0.61
    MigrationBuilder
    -0.57
    BufferException
    -0.56
     InputDecoration
    -0.56
    IUrlHelper
    -0.53
    SuspendLayout
    -0.52
    OrBuilder
    -0.50
    POSITIVE LOGITS
    <h1>
    0.44
    package
    0.42
     corporativa
    0.39
     virksom
    0.38
    ksom
    0.36
    Informe
    0.36
    INDIAN
    0.36
    inf
    0.36
    <strong>
    0.35
    <b>
    0.34
    Activations Density 0.106%

    No Known Activations