Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 11292
    Prev
    Next
    INDEX
    Explanations

    ab-related terms in the context of scientific discussions

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

    Preceding "bc," "ols," "ale," or "ins"

    np_acts-logits-general · gemini-2.0-flash

    cryoablation, catechins

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    an
    -1.20
    u
    -0.98
    ه
    -0.85
    ar
    -0.82
    ي
    -0.82
    o
    -0.79
    es
    -0.76
    i
    -0.73
    in
    -0.72
    on
    -0.71
    POSITIVE LOGITS
    IUrlHelper
    0.93
    tagext
    0.89
     Roskov
    0.84
    참고
    0.75
    GraphicsUnit
    0.74
    WebElementEntity
    0.71
     BoxFit
    0.69
    MigrationBuilder
    0.69
     cohomology
    0.67
     USG
    0.66
    Activations Density 0.261%

    No Known Activations