© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 427
    Prev
    Next
    INDEX
    Explanations

    markers that indicate the beginning or organization of sections in a document

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

    numerical values and associated annotations

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

    commas and parentheses

    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
     كومونز
    -1.01
    although
    -0.82
     although
    -0.80
    though
    -0.74
    which
    -0.74
    AnchorStyles
    -0.72
     endwhile
    -0.71
     which
    -0.68
    despite
    -0.67
    while
    -0.67
    POSITIVE LOGITS
    _,
    0.69
    ","");
    0.69
     ,
    0.67
    *,
    0.67
     ...,
    0.66
    ','
    0.65
     ?',
    0.63
     ',
    0.62
     *,
    0.61
    icznego
    0.60
    Activations Density 0.314%

    No Known Activations