© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1673
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ′
    -0.31
     extérieure
    -0.31
     Procedure
    -0.31
     dator
    -0.30
     Coin
    -0.29
     supporting
    -0.29
     responsabilidad
    -0.28
    ff
    -0.28
     приз
    -0.28
     direction
    -0.28
    POSITIVE LOGITS
    TypedDataSet
    0.79
    RenderAtEndOf
    0.69
    AddTagHelper
    0.68
    
    0.67
     InputDecoration
    0.63
    tvguidetime
    0.62
    ThroughAttribute
    0.61
    ValueStyle
    0.61
     faſt
    0.60
     ويكيپيديا
    0.59
    Activations Density 0.637%

    No Known Activations