© 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. 15-GEMMASCOPE-RES-16K
    11. 2051
    Prev
    Next
    INDEX
    Explanations

    numerical values or measurements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     חיצוניים
    -1.00
    Халык
    -0.73
     وتسجيلات
    -0.70
    Hauptartikel
    -0.67
    extAlignment
    -0.65
    Välislingid
    -0.64
     pinulongan
    -0.64
    ,
    -0.63
    Gir
    -0.62
     समीक्षाओं
    -0.60
    POSITIVE LOGITS
    ("%.
    0.83
    CloseOperation
    0.81
    )}.
    0.81
    ()].
    0.79
    __).
    0.77
    ">.
    0.76
    /*.
    0.76
    */].
    0.74
     $-.
    0.73
     }}$.
    0.73
    Activations Density 0.358%

    No Known Activations