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. 13-GEMMASCOPE-RES-16K
    6. 345
    Prev
    Next
    INDEX
    Explanations

    some form of structured data or programming elements

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

    numeric data, measurements, or values in various formats including integers, decimals, or numbers in text.

    oai_token-act-pair · gpt-4oTriggered by @timna
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aarrggbb
    -0.79
    OGND
    -0.69
    httphttps
    -0.68
    styleType
    -0.66
    Билгалдахарш
    -0.62
    findpost
    -0.61
    LookAnd
    -0.60
    IntoConstraints
    -0.59
     estekak
    -0.59
    Lähteet
    -0.55
    POSITIVE LOGITS
     electrolux
    0.48
     fahren
    0.48
     resultCode
    0.48
    ècie
    0.48
    meneu
    0.47
     Gattung
    0.47
     standing
    0.46
     seeded
    0.45
     judging
    0.45
    濛
    0.45
    Activations Density 1.007%

    No Known Activations