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. 16-GEMMASCOPE-RES-16K
    6. 2828
    Prev
    Next
    INDEX
    Explanations

    variadic functions or methods that accept a variable number of parameters

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     HttpServlet
    -0.61
     estekak
    -0.56
     secours
    -0.53
     fédé
    -0.52
     découver
    -0.51
     représentants
    -0.51
     getInstance
    -0.50
     féminine
    -0.50
     âmes
    -0.50
    gonic
    -0.50
    POSITIVE LOGITS
    enumi
    0.69
    下载附件
    0.67
    BagConstraints
    0.64
    </caption>
    0.63
    tail
    0.63
     AssemblyCulture
    0.63
     autorytatywna
    0.62
    ImageContext
    0.59
     tail
    0.56
    ngths
    0.55
    Activations Density 0.167%

    No Known Activations