© 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. 1-GEMMASCOPE-RES-16K
    11. 14717
    Prev
    Next
    INDEX
    Explanations

    instances of the word "leading" or its variations that signify dominance in a field or area

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.57
    rawDesc
    -0.56
    matchCondition
    -0.56
     encar
    -0.54
    Hozzáférés
    -0.53
    modb
    -0.52
    isset
    -0.48
    χή
    -0.47
    methe
    -0.47
    [:,
    -0.46
    POSITIVE LOGITS
     leading
    1.96
    leading
    1.76
     Leading
    1.75
    Leading
    1.69
    LEADING
    1.33
     füh
    1.07
     веду
    0.96
     foremost
    0.79
    PRNewswire
    0.74
    领先
    0.74
    Activations Density 0.074%

    No Known Activations