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. 1648
    Prev
    Next
    INDEX
    Explanations

    quantitative data and numerical representations in the text

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

    Numbers followed by a forward slash

    np_acts-logits-general · gemini-2.0-flash

    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
     third
    -0.75
     Third
    -0.73
    thirds
    -0.69
     triples
    -0.68
     thirds
    -0.67
    third
    -0.67
    3
    -0.64
     Thirdly
    -0.63
     dritten
    -0.62
    สาม
    -0.62
    POSITIVE LOGITS
     EconPapers
    0.61
    jsonwebtoken
    0.57
     forties
    0.54
    ylabel
    0.54
     favore
    0.53
    Чет
    0.52
    UrlResolution
    0.51
    ❹
    0.51
    jspx
    0.50
    CGRectMake
    0.49
    Activations Density 0.398%

    No Known Activations