© 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. 3316
    Prev
    Next
    INDEX
    Explanations

    instances of punctuation and apostrophes, indicating informal or conversational text

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

    Apostrophes, periods, or "eta" followed by letters

    np_acts-logits-general · gemini-2.0-flash

    possessive 's or closing quotes

    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
     للاسماء
    -0.81
     مشين
    -0.70
     ***!
    -0.64
    UnsafeEnabled
    -0.62
    )";
    -0.62
    RetentionPolicy
    -0.61
     الحره
    -0.60
    `).
    -0.60
    BorderFactory
    -0.59
    DockStyle
    -0.59
    POSITIVE LOGITS
    “
    0.59
     sherds
    0.56
     sputnik
    0.54
     Oedipus
    0.53
    <em>
    0.51
    Jîn
    0.51
     authorship
    0.51
     stoneware
    0.50
    s
    0.50
     Sodom
    0.50
    Activations Density 0.076%

    No Known Activations