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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6765
    Prev
    Next
    INDEX
    Explanations

    references to health-related deficiencies and their causes

    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
    rawDesc
    -0.53
    Билгалдахарш
    -0.48
    
    -0.46
    __':
    -0.45
    parsedMessage
    -0.44
    astéroïdes
    -0.44
    __':
    -0.43
    verwijspagina
    -0.42
    andExpect
    -0.39
    ferrer
    -0.39
    POSITIVE LOGITS
     cover
    3.64
     covers
    3.27
    Cover
    3.25
    cover
    3.20
     Cover
    3.20
     COVER
    3.19
     covering
    3.16
     Covering
    2.95
    COVER
    2.95
     covered
    2.94
    Activations Density 1.080%

    No Known Activations