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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 29680
    Prev
    Next
    INDEX
    Explanations

    actions related to coordination, support, and development in professional settings

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

    managing, performing, coordinating tasks

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     queſta
    -0.76
    ValueStyle
    -0.73
    IsContent
    -0.73
     }{@
    -0.71
    SpringBootTest
    -0.69
    TypedDataSet
    -0.69
     dAtA
    -0.64
     endregion
    -0.63
    principalTable
    -0.63
    NameInMap
    -0.63
    POSITIVE LOGITS
    raszam
    0.35
     also
    0.35
     and
    0.33
     Constitución
    0.33
    raszamy
    0.32
     routinely
    0.32
     Relaciones
    0.31
     promotional
    0.31
     wewnętr
    0.30
     négociations
    0.29
    Activations Density 0.010%

    No Known Activations