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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 1273
    Prev
    Next
    INDEX
    Explanations

    references to news sources and reporting institutions

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

    Follows a capitalized news source/agency token

    np_acts-logits-general · gemini-2.0-flash

    news agencies and publications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '<?
    -0.59
    kespea
    -0.54
    _;
    -0.47
    roth
    -0.47
    tiere
    -0.46
    inys
    -0.46
     makeStyles
    -0.45
     ')[
    -0.45
    anship
    -0.45
     freue
    -0.45
    POSITIVE LOGITS
     للاسماء
    0.73
    ########.
    0.73
    DockStyle
    0.71
    AntiForgeryToken
    0.69
     vectorielle
    0.67
     vectorielles
    0.66
    IntoConstraints
    0.64
     resourceCulture
    0.64
    EDEFAULT
    0.63
    expandindo
    0.61
    Activations Density 0.158%

    No Known Activations