Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-2B
    3. 7-GEMMASCOPE-TRANSCODER-16K
    4. 7096
    Prev
    Next
    INDEX
    Explanations

    code snippets containing the keywords "get" and "set", especially with higher activation when both are present together

    oai_token-act-pair · gemini-2.0-flash

    set

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-transcoders/layer_7/width_16k/average_l0_70
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.ln2.hook_normalized
    Architecture
    jumprelu_transcoder
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.59
    IonicModule
    -0.56
    Indep
    -0.54
    
    -0.50
     Савезне
    -0.50
    遣
    -0.50
     مواليد
    -0.48
     Alembic
    -0.48
    typeorm
    -0.47
    |}\
    -0.47
    POSITIVE LOGITS
     replays
    0.60
    scryfall
    0.58
    kháu
    0.57
     NSError
    0.56
    bParam
    0.55
    IsMutable
    0.55
     محفوظة
    0.54
    uVar
    0.54
     ModelExpression
    0.52
    最快更新
    0.50
    Activations Density 1.186%

    No Known Activations