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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-GEMMASCOPE-RES-16K
    6. 6224
    Prev
    Next
    INDEX
    Explanations

    numerical values, particularly in the context of statistical or quantitative information

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     épaules
    -0.75
     genoux
    -0.73
    __).
    -0.71
    Bae
    -0.69
    wanne
    -0.68
     SqlDbType
    -0.67
     wireType
    -0.67
     varandra
    -0.67
    "]),
    -0.66
    IGraphics
    -0.66
    POSITIVE LOGITS
     MotionEvent
    0.78
    dataclass
    0.73
     himo
    0.71
    jší
    0.69
     noqa
    0.66
    ArgsConstructor
    0.65
     Dogg
    0.65
    δώ
    0.65
    DataAnnotations
    0.64
    lamy
    0.63
    Activations Density 0.830%

    No Known Activations