© 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. 1163
    Prev
    Next
    INDEX
    Explanations

    specific terminology related to technology and software contexts

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

    Text followed by a descriptive tag

    np_acts-logits-general · gemini-2.0-flash

    abstracts and summaries

    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
     Wiktionnaire
    -0.71
     HttpNotFound
    -0.70
    inafter
    -0.69
     Hemisphere
    -0.68
    lapping
    -0.66
    ercice
    -0.65
     myſelf
    -0.65
     homoto
    -0.65
    neſs
    -0.64
    ighed
    -0.64
    POSITIVE LOGITS
    etheless
    0.83
    parsedMessage
    0.78
    oltre
    0.72
    éfono
    0.72
    aimana
    0.67
    rrggbb
    0.66
    makeConstraints
    0.60
    cerely
    0.59
    pherd
    0.59
    resizingMask
    0.57
    Activations Density 1.668%

    No Known Activations