© 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. 31-GEMMASCOPE-RES-16K
    11. 14695
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "kick" and its variations in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "kick" or its variations in different contexts (kick off, kickdown, kicked, etc.).

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    prc
    -0.34
     initComponents
    -0.32
    module
    -0.29
    var
    -0.28
    солю
    -0.28
    nau
    -0.28
     слой
    -0.28
    GeneratedValue
    -0.28
    oh
    -0.28
    MathML
    -0.28
    POSITIVE LOGITS
     kick
    1.47
     kicked
    1.43
    Kick
    1.41
     Kick
    1.41
     KICK
    1.41
    kick
    1.40
     kicking
    1.36
     kicks
    1.31
    kicks
    1.14
     Kicks
    1.13
    Activations Density 0.034%

    No Known Activations