© 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. 22-GEMMASCOPE-RES-16K
    11. 11318
    Prev
    Next
    INDEX
    Explanations

    references to the name "Bill" and its variants in various contexts

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

    Tokens frequently preceding names

    np_acts-logits-general · gemini-2.0-flash

    Bill followed by last name

    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
    HideFlags
    -0.74
    ︎
    -0.73
     JpaRepository
    -0.72
     InputDecoration
    -0.71
    BeginInit
    -0.71
    存于互联网档案馆
    -0.69
    ++
    -0.68
    ^(@)
    -0.65
     BoxDecoration
    -0.65
     yyr
    -0.65
    POSITIVE LOGITS
     Gates
    0.73
    boards
    0.67
    Gates
    0.65
     Bill
    0.60
     Bills
    0.60
     Clinton
    0.58
     gates
    0.56
    iton
    0.55
    owing
    0.55
     Belich
    0.54
    Activations Density 0.086%

    No Known Activations