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. 20-GEMMASCOPE-RES-16K
    6. 2679
    Prev
    Next
    INDEX
    Explanations

    programming language identifiers and related syntax elements

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

    File extensions: ".java", ".py", ".cpp"

    np_acts-logits-general · gemini-2.0-flash

    programming languages in code files

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    цезда
    -0.91
     Exacts
    -0.89
    ItemBackground
    -0.88
    IntoConstraints
    -0.85
     InputDecoration
    -0.83
    URLException
    -0.82
    UrlResolution
    -0.81
     Himo
    -0.81
     WebDriverWait
    -0.80
    Ӕ
    -0.79
    POSITIVE LOGITS
    <eos>
    0.97
    ↵
    0.67
    ↵↵
    0.63
    ↵↵↵
    0.59
    ↵↵↵↵
    0.54
    ↵↵↵↵↵
    0.52
    ↵↵↵↵↵↵
    0.50
    ↵↵↵↵↵↵↵↵
    0.48
    ↵↵↵↵↵↵↵↵↵
    0.44
    ↵↵↵↵↵↵↵
    0.43
    Activations Density 0.086%

    No Known Activations