Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 5859
    Prev
    Next
    INDEX
    Explanations

    information related to dance education and the credentials of dance educators

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

    dance or dancing

    np_acts-logits-general · gemini-2.0-flash

    dance performance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Económica
    -0.52
    psack
    -0.52
    XIM
    -0.49
    談社
    -0.47
    üstet
    -0.47
    utnik
    -0.47
    Shelf
    -0.46
    Hypo
    -0.46
    UserScript
    -0.45
    riwal
    -0.45
    POSITIVE LOGITS
     dance
    2.67
     danced
    2.41
     dancing
    2.39
     Dance
    2.33
     dancers
    2.28
     dances
    2.27
    dance
    2.22
     DANCE
    2.20
     dancer
    2.15
    Dance
    2.15
    Activations Density 0.146%

    No Known Activations