© 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. 8298
    Prev
    Next
    INDEX
    Explanations

    elements related to structured data or XML content

    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
     ProtoMessage
    -0.36
     Erkrank
    -0.30
    IntoConstraints
    -0.26
    AndEndTag
    -0.25
    rawDesc
    -0.24
     sicheren
    -0.24
     stehenden
    -0.24
     möglichen
    -0.23
    Попис
    -0.23
     Erkrankungen
    -0.23
    POSITIVE LOGITS
     French
    0.95
    French
    0.89
     France
    0.86
     french
    0.85
     FRENCH
    0.83
     francus
    0.83
    France
    0.82
     franceses
    0.82
    法國
    0.82
     Ligue
    0.82
    Activations Density 8.114%

    No Known Activations