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. 5-GEMMASCOPE-RES-16K
    6. 2540
    Prev
    Next
    INDEX
    Explanations

    mathematical terms or symbols indicative of equations and functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |}{$
    -0.66
     konkre
    -0.60
     vnto
    -0.58
     قار
    -0.57
     voic
    -0.57
     Charlie
    -0.55
    aven
    -0.55
     Gymnas
    -0.55
    LayoutPanel
    -0.55
    __[
    -0.55
    POSITIVE LOGITS
    OrWhiteSpace
    0.66
     onlyOwner
    0.62
    jdt
    0.62
    EDEFAULT
    0.61
    enumi
    0.60
    oxone
    0.58
    GraphicsUnit
    0.58
    bootstrapcdn
    0.57
    walde
    0.56
     balanceOf
    0.56
    Activations Density 0.541%

    No Known Activations