© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6747
    Prev
    Next
    INDEX
    Explanations

    events related to public gatherings or ceremonies

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

    event details like guest lists, dinner invitations, and event logistics.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ktive
    -0.38
    MathML
    -0.38
     архивлан
    -0.35
     Fórmula
    -0.34
    baiki
    -0.33
    irin
    -0.32
     IEnumerator
    -0.32
    __*/
    -0.31
     réguli
    -0.31
     weakness
    -0.30
    POSITIVE LOGITS
     dinner
    0.72
    Dinner
    0.71
     Dinner
    0.67
     luncheon
    0.66
    dinner
    0.61
     gala
    0.61
     banquet
    0.57
     DINNER
    0.57
     Luncheon
    0.57
     reception
    0.54
    Activations Density 0.066%

    No Known Activations