© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 446
    Prev
    Next
    INDEX
    Explanations

    structured data or code snippets related to functions or tables in documents

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

    Symbols indicating changes or types

    np_acts-logits-general · gemini-2.0-flash

    punctuation and symbols

    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
    ".
    -0.86
    .";
    -0.86
     كومونز
    -0.85
    .",
    -0.84
    !")
    -0.73
    '},
    -0.72
    Datuak
    -0.69
    "):
    -0.67
    ?
    -0.67
    %</
    -0.66
    POSITIVE LOGITS
    ꒳
    0.76
     ddelweddau
    0.69
    ethene
    0.68
     glucocortico
    0.66
     chlorophyll
    0.64
     monocytes
    0.62
     defStyleAttr
    0.60
     &&
    0.60
     witchcraft
    0.60
     Margot
    0.59
    Activations Density 0.852%

    No Known Activations