© 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. 10661
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and syntax, particularly from programming languages or code structures

    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
     Christie
    -0.72
     Dolan
    -0.71
    Christie
    -0.67
     Albany
    -0.63
     Qiu
    -0.63
    Albany
    -0.61
     Moser
    -0.60
     Arcadia
    -0.60
     Kah
    -0.59
     Kris
    -0.59
    POSITIVE LOGITS
     Weymouth
    0.63
     Franck
    0.62
     Caval
    0.62
     ByteArray
    0.62
     Cochran
    0.59
    Coch
    0.59
     Gaunt
    0.59
    Caval
    0.59
     Hough
    0.58
    Franck
    0.58
    Activations Density 1.453%

    No Known Activations