© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 122204
    Prev
    Next
    INDEX
    Explanations

    references to the concept of pace or pacing within the text

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

    describing the pace

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <bos>
    -0.55
     true
    -0.44
     inteiro
    -0.42
     thousand
    -0.40
    Conclusión
    -0.40
     whole
    -0.38
     third
    -0.38
    Voir
    -0.37
     Foreign
    -0.36
     completely
    -0.35
    POSITIVE LOGITS
    Pace
    1.23
     Pace
    1.23
     pace
    1.16
     PACE
    1.11
    PACE
    0.91
    paced
    0.90
     pacing
    0.90
     paced
    0.89
     paces
    0.84
    pace
    0.78
    Activations Density 0.005%

    No Known Activations