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. 11010
    Prev
    Next
    INDEX
    Explanations

    numerical values, programming symbols, and names of institutions and locations

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

    Comes after a university or college name

    np_acts-logits-general · gemini-2.0-flash

    American Pathologists

    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
    webElementXpaths
    -0.55
    RenderAtEndOf
    -0.51
    جمعیت
    -0.48
    execSQL
    -0.45
     enc
    -0.44
    dição
    -0.44
     espac
    -0.43
     cetera
    -0.42
     conséquent
    -0.42
    RetentionPolicy
    -0.42
    POSITIVE LOGITS
    gonic
    0.76
    ंदीखरीदारी
    0.63
     CX
    0.61
     Cs
    0.61
    CMY
    0.61
    出版年
    0.60
     CFC
    0.58
    RTSN
    0.58
    raszamy
    0.57
    fines
    0.57
    Activations Density 0.845%

    No Known Activations