© 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. 20-GEMMASCOPE-RES-16K
    11. 15379
    Prev
    Next
    INDEX
    Explanations

    the beginning of formatted sections in documents, often indicating structured content

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

    Punctuation and symbols

    np_acts-logits-general · gemini-2.0-flash

    numbers, dates, and punctuation

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    NUMX
    -1.17
    ſelf
    -1.04
     iſt
    -1.03
     ―――――
    -1.02
    ^(@)
    -1.02
     $_"
    -0.98
     Efq
    -0.95
    */;
    -0.95
     myſelf
    -0.93
     ***/
    -0.91
    POSITIVE LOGITS
    <eos>
    0.69
    ?
    0.65
    !
    0.64
    ↵
    0.61
     ^
    0.61
    <bos>
    0.60
    ^
    0.60
    (
    0.59
    >
    0.58
     ;
    0.57
    Activations Density 0.179%

    No Known Activations