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. 4856
    Prev
    Next
    INDEX
    Explanations

    references to the term "Bel" or related variations in content

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

    starting with "Bel"

    np_acts-logits-general · gemini-2.0-flash

    words starting with "Bel"

    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
     OFDb
    -0.78
    SourceChecksum
    -0.71
    hysema
    -0.66
     geweest
    -0.62
    Fordítás
    -0.62
     ComVisible
    -0.58
     himo
    -0.58
    LikeLike
    -0.58
    aarrggbb
    -0.57
    Derbyniad
    -0.56
    POSITIVE LOGITS
     BEL
    0.88
     Bel
    0.85
    Bel
    0.74
     bel
    0.73
    BEL
    0.59
    bel
    0.58
     Marra
    0.56
     Belvedere
    0.56
     BELL
    0.55
     Belo
    0.53
    Activations Density 0.056%

    No Known Activations