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. 10800
    Prev
    Next
    INDEX
    Explanations

    the presence of punctuation, specifically commas

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

    The token ","

    np_acts-logits-general · gemini-2.0-flash

    comma followed by a new clause

    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
     continúas
    -0.86
     كومونز
    -0.84
     تانيه
    -0.78
    findpost
    -0.76
    
    -0.72
    存于互联网档案馆
    -0.71
    tvguidetime
    -0.71
    DoubleQuotes
    -0.68
    kháu
    -0.68
     iſt
    -0.67
    POSITIVE LOGITS
    M
    0.56
     mukaan
    0.45
    m
    0.45
    2
    0.44
     M
    0.44
    migrations
    0.44
    S
    0.44
    D
    0.43
    Areas
    0.42
     что
    0.42
    Activations Density 0.137%

    No Known Activations