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. 16-GEMMASCOPE-RES-16K
    6. 16058
    Prev
    Next
    INDEX
    Explanations

    references to charts, objects, and their properties in data processing contexts

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

    code, IDs, or questions

    np_acts-logits-general · gemini-2.0-flash

    chart or URL, id, date

    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
    AccessorTable
    -1.03
    +#+#
    -0.97
    RegressionTest
    -0.93
    ftagPool
    -0.87
     disambiguazione
    -0.77
    UnusedPrivate
    -0.73
     виправивши
    -0.72
    aarrggbb
    -0.70
    WebServlet
    -0.70
    __*/
    -0.70
    POSITIVE LOGITS
     of
    0.53
    事です
    0.51
     that
    0.49
     بيها
    0.48
     carried
    0.46
    ناية
    0.45
    ;
    0.44
    addContainerGap
    0.43
    ,
    0.43
     produced
    0.41
    Activations Density 0.345%

    No Known Activations