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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 8086
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "kick" in various contexts, often related to initiating or starting actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     لئے
    -0.62
    WebElementEntity
    -0.60
    ticoli
    -0.58
    venus
    -0.57
    impresa
    -0.57
     بتاريخ
    -0.56
     doccia
    -0.55
    vores
    -0.55
    genomen
    -0.54
     път
    -0.53
    POSITIVE LOGITS
     kick
    3.97
     Kick
    3.54
    kick
    3.48
     kicks
    3.46
     kicked
    3.40
     KICK
    3.40
    Kick
    3.39
     kicking
    3.30
    kicks
    2.85
     Kicks
    2.73
    Activations Density 0.039%

    No Known Activations