© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 722
    Prev
    Next
    INDEX
    Explanations

    proper nouns, especially related to names, locations, and events

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

    the mention of the name "Sundaram" or variants thereof

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

    Sund, Sundance, Sond, Mira, ensemble

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ab
    -0.58
     res
    -0.53
     ap
    -0.51
    ,
    -0.51
     Hart
    -0.50
    .
    -0.50
     (
    -0.50
     i
    -0.48
     es
    -0.48
     future
    -0.47
    POSITIVE LOGITS
     Sund
    1.08
    ſelves
    1.00
     SUND
    1.00
    Sund
    0.95
     Chriftian
    0.94
    SUND
    0.92
     Monfieur
    0.91
    sund
    0.89
    DockStyle
    0.87
     ་་
    0.83
    Activations Density 0.017%

    No Known Activations