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. 2262
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical functions and operations

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

    Mathematical or product derivatives

    np_acts-logits-general · gemini-2.0-flash

    take the derivative or product

    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
     vPvB
    -0.57
     nahilalakip
    -0.51
    υσ
    -0.51
    ellemző
    -0.49
    Kapp
    -0.49
     bambú
    -0.49
    Fontes
    -0.48
    ⪯
    -0.47
     Methodology
    -0.46
     Biro
    -0.46
    POSITIVE LOGITS
    rungsseite
    0.77
     product
    0.71
     derivative
    0.70
    principalTable
    0.67
    RenderAtEndOf
    0.64
    ViewFeatures
    0.63
    product
    0.62
    AndroidJUnit
    0.62
    produto
    0.61
    PRODUCT
    0.61
    Activations Density 1.404%

    No Known Activations