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. 10053
    Prev
    Next
    INDEX
    Explanations

    code structures and their access modifiers in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     Wal
    -0.54
    prising
    -0.54
     “
    -0.50
     "
    -0.48
     أح
    -0.48
    ніципалі
    -0.47
     Hartman
    -0.47
    -
    -0.46
     reloaded
    -0.46
    jacking
    -0.46
    POSITIVE LOGITS
     متعلقه
    0.90
    enumi
    0.88
    migrationBuilder
    0.87
    CloseOperation
    0.86
    </caption>
    0.83
     pleaſure
    0.80
    Personensuche
    0.79
     وتسجيلات
    0.74
     IndexPath
    0.74
    __(/*!
    0.74
    Activations Density 0.012%

    No Known Activations