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. 14280
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and terms related to fractional derivatives and polynomials

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     שוליים
    -0.42
     insecto
    -0.41
    aarrggbb
    -0.40
     condi
    -0.38
    phora
    -0.38
     insect
    -0.38
    ู้
    -0.37
     daly
    -0.37
    hindu
    -0.37
    Biblia
    -0.36
    POSITIVE LOGITS
     order
    1.24
    order
    1.23
     orders
    1.19
     Order
    1.18
     Orders
    1.17
    Order
    1.16
     ORDER
    1.16
     higher
    1.11
    Orders
    1.09
    orders
    1.04
    Activations Density 1.515%

    No Known Activations