© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1343
    Prev
    Next
    INDEX
    Explanations

    references to legal documents or citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hozzáférés
    -0.46
    出版年
    -0.38
    ppuden
    -0.36
    MigrationBuilder
    -0.36
    >>();
    -0.35
    ่านั้น
    -0.35
     theils
    -0.34
    ScopeManager
    -0.34
     bits
    -0.33
     sorted
    -0.33
    POSITIVE LOGITS
     vii
    0.99
     vi
    0.97
     ix
    0.96
     viii
    0.95
    viii
    0.95
     iii
    0.92
    vii
    0.92
    xii
    0.91
    xiv
    0.90
    xiii
    0.90
    Activations Density 0.603%

    No Known Activations