© 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. 6120
    Prev
    Next
    INDEX
    Explanations

    numerical patterns and structure in equations or data lists

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

    Commas followed by numbers

    np_acts-logits-general · gemini-2.0-flash

    sequences of numbers and commas

    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
    ,
    -0.77
    …
    -0.72
    '
    -0.71
     lenker
    -0.69
    -0.66
    ...
    -0.63
    ?
    -0.60
    .
    -0.59
    "
    -0.57
    :])
    -0.56
    POSITIVE LOGITS
    .,,
    0.76
    ,-,
    0.75
    omitempty
    0.75
     ...,
    0.74
     виправивши
    0.73
    =,
    0.73
    зулта
    0.72
     disponibilités
    0.72
    __,
    0.72
    ,,,,
    0.70
    Activations Density 1.020%
    No Known Activations