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. 15318
    Prev
    Next
    INDEX
    Explanations

    coding or script-like syntax and mathematical notation

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

    the beginning-of-sequence marker, i.e., starts of new documents or sections.

    oai_token-act-pair · gpt-5Triggered 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
    AnchorStyles
    -0.66
    AndEndTag
    -0.66
    InjectAttribute
    -0.64
    bleau
    -0.64
    DMETHOD
    -0.63
    protoimpl
    -0.61
     كومونز
    -0.61
     Waray
    -0.60
    thâu
    -0.60
    InputBorder
    -0.60
    POSITIVE LOGITS
     prisão
    0.56
    frontmatter
    0.54
    ↵↵
    0.53
    تقاوى
    0.50
    ↵↵↵↵
    0.50
    <b>
    0.48
    gebühr
    0.48
     cerah
    0.47
     ,
    0.47
    <eos>
    0.47
    Activations Density 0.363%

    No Known Activations