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. 14560
    Prev
    Next
    INDEX
    Explanations

    references, citations, and numerical data in a text

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

    Punctuation at the end of a line

    np_acts-logits-general · gemini-2.0-flash

    punctuation and numbers

    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
     mergeFrom
    -0.58
    ?',
    -0.56
    ()',
    -0.54
    '}),
    -0.54
    二是
    -0.54
     Мексичка
    -0.54
     "";
    
    -0.53
    !';
    -0.53
    eby
    -0.52
    !',
    -0.52
    POSITIVE LOGITS
    ↵↵↵↵
    0.83
    ↵↵↵↵↵↵
    0.81
    ↵↵↵↵↵
    0.78
    ↵↵↵
    0.78
    ↵↵
    0.77
    ↵↵↵↵↵↵↵
    0.75
    ↵↵↵↵↵↵↵↵
    0.73
    ↵↵↵↵↵↵↵↵↵
    0.68
    ↵↵↵↵↵↵↵↵↵↵
    0.67
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.64
    Activations Density 0.630%

    No Known Activations