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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 10-GEMMASCOPE-RES-16K
    6. 12624
    Prev
    Next
    INDEX
    Explanations

    references to data structures and their properties in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.94
     nahilalakip
    -0.88
     autorytatywna
    -0.86
     resourceCulture
    -0.85
    contentLoaded
    -0.84
    verwijspagina
    -0.83
    AccessorTable
    -0.82
     للاسماء
    -0.81
    aarrggbb
    -0.79
    parsedMessage
    -0.76
    POSITIVE LOGITS
    covi
    0.41
     NDEBUG
    0.41
     ultimately
    0.39
     pars
    0.38
    Remote
    0.38
    xtick
    0.37
     Elli
    0.37
     thôi
    0.36
    чало
    0.35
    mple
    0.35
    Activations Density 1.448%

    No Known Activations