© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1391
    Prev
    Next
    INDEX
    Explanations

    closing braces and related syntax structures in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    তথ্যসূত্র
    -0.74
    esgue
    -0.58
    inafter
    -0.55
     mengangg
    -0.54
    tyfik
    -0.51
     Galla
    -0.51
     correctes
    -0.49
    Javadoc
    -0.49
     figurative
    -0.48
    Dono
    -0.48
    POSITIVE LOGITS
    WindowConstants
    0.72
     AssemblyCulture
    0.61
     NSCoder
    0.59
     return
    0.59
    writeFieldEnd
    0.59
    return
    0.58
     maaf
    0.53
    例文帳に追加
    0.52
    Nope
    0.52
    ]";
    0.52
    Activations Density 0.055%

    No Known Activations