© 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. 9007
    Prev
    Next
    INDEX
    Explanations

    phrases expressing uncertainty or inquiry

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

    Followed by "if"

    np_acts-logits-general · gemini-2.0-flash

    only if / determine whether

    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
    for
    -0.52
    but
    -0.52
    FROM
    -0.49
     eventuali
    -0.49
    from
    -0.49
    would
    -0.46
    about
    -0.46
    But
    -0.45
    Depending
    -0.45
    goto
    -0.45
    POSITIVE LOGITS
    InjectAttribute
    1.06
     للاسماء
    0.99
     esternos
    0.95
    ThroughAttribute
    0.95
    ագրություններ
    0.92
     وتسجيلات
    0.91
     مرئيه
    0.91
     ویکی‌پدی
    0.91
     ISTAT
    0.89
    ViewFeatures
    0.89
    Activations Density 0.299%

    No Known Activations