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 - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 3346
    Prev
    Next
    INDEX
    Explanations

    HTML meta and link elements related to document metadata and resources

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

    Code parameters or configuration names

    np_acts-logits-general · gemini-2.0-flash

    XML/HTML attributes and values

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsxFileName
    -0.40
    HomeAsUpEnabled
    -0.39
     déroule
    -0.39
    class
    -0.36
     Photocase
    -0.35
    下载附件
    -0.35
     comerci
    -0.34
     proveedor
    -0.34
    britanni
    -0.34
    ClCompile
    -0.33
    POSITIVE LOGITS
     name
    0.80
    makeText
    0.61
     ब्रेकडाउन
    0.60
    FlatAppearance
    0.56
     noiva
    0.53
    Personensuche
    0.52
    enumii
    0.51
    Архівовано
    0.51
    bindValue
    0.51
    migrationBuilder
    0.50
    Activations Density 0.165%

    No Known Activations