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

    Neuronpedia

    APICircuit 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. 38847
    Prev
    Next
    INDEX
    Explanations

    references to health-related issues impacting Asian American and Pacific Islander families, particularly those with sexual minority parents

    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
    UrlResolution
    -0.57
     ब्रेकडाउन
    -0.50
     wireType
    -0.47
    URLException
    -0.46
    WireFormatLite
    -0.46
    Hochspringen
    -0.44
    =$?
    -0.44
     AssemblyCulture
    -0.44
    migrationBuilder
    -0.43
    RenderAtEndOf
    -0.43
    POSITIVE LOGITS
    Ensure
    0.49
     profiled
    0.43
    最快更新
    0.41
     CreateTagHelper
    0.40
     putus
    0.38
     Ensure
    0.38
     besoins
    0.38
     adolescents
    0.38
     ensuring
    0.38
    glected
    0.38
    Activations Density 0.044%

    No Known Activations