© 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. 41-GEMMASCOPE-RES-16K
    11. 7025
    Prev
    Next
    INDEX
    Explanations

    terms related to subcategories or subdivisions within broader contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     libraries
    -0.69
     watches
    -0.68
     lists
    -0.68
     houses
    -0.67
     cities
    -0.66
     charts
    -0.66
     fruits
    -0.66
     lines
    -0.65
     languages
    -0.65
     villages
    -0.65
    POSITIVE LOGITS
    albums
    0.43
    models
    0.41
    deals
    0.41
    copies
    0.41
    products
    0.41
    items
    0.40
    bundles
    0.40
    cases
    0.40
    devices
    0.40
    markets
    0.40
    Activations Density 1.084%

    No Known Activations