© 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. 7828
    Prev
    Next
    INDEX
    Explanations

    complex relationships and dependencies between concepts or entities

    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
     Combination
    -0.56
     Combinations
    -0.51
    Combination
    -0.50
     Differences
    -0.50
    tachment
    -0.50
     Associations
    -0.49
    ThroughAttribute
    -0.49
    combination
    -0.49
    Association
    -0.48
    combinations
    -0.47
    POSITIVE LOGITS
     closely
    0.86
     related
    0.84
     linked
    0.70
     interrelated
    0.69
     intertwined
    0.67
     intimately
    0.65
     connected
    0.63
     mutually
    0.63
    related
    0.63
     inter
    0.62
    Activations Density 1.286%

    No Known Activations