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 - 65k
    5. 20-GEMMASCOPE-RES-65K
    6. 896
    Prev
    Next
    INDEX
    Explanations

    terms related to different forms of sculptures and their artistic representations

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

    terms related to sculpture and sculpting

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

    creation, formation, or discovery

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     ویکی‌پدیا
    -0.95
    findpost
    -0.88
     NDL
    -0.76
     оригіналу
    -0.76
    ToProps
    -0.74
    APOLIS
    -0.72
     informée
    -0.71
     }^{(
    -0.69
    withIdentifier
    -0.69
    存于互联网档案馆
    -0.69
    POSITIVE LOGITS
    ième
    0.69
    s
    0.63
     musikk
    0.54
    ska
    0.53
    .........
    0.52
     PropTypes
    0.52
    uality
    0.51
    dbf
    0.51
    ------
    0.51
    XmlSchema
    0.51
    Activations Density 0.066%

    No Known Activations