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
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 291
    Prev
    Next
    INDEX
    Explanations

    specific arrangements and configurations in data structures or layouts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     وتسجيلات
    -0.38
    Rüyada
    -0.38
    RegistryLite
    -0.35
     relações
    -0.34
     orel
    -0.33
     Egan
    -0.33
    nologue
    -0.32
     Arhivirano
    -0.32
     >=",
    -0.31
    rawDesc
    -0.31
    POSITIVE LOGITS
     rows
    0.93
     Rows
    0.87
     row
    0.84
     Row
    0.68
    gridColumn
    0.67
     baris
    0.67
     Reihen
    0.66
    BagLayout
    0.66
    LayoutPanel
    0.63
    RowCount
    0.62
    Activations Density 0.310%

    No Known Activations