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. 13329
    Prev
    Next
    INDEX
    Explanations

    LaTeX formatting and structure in scientific text

    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
     femininos
    -0.68
     femininas
    -0.66
     comerciais
    -0.61
     digitais
    -0.58
    LikeLike
    -0.57
     protoimpl
    -0.56
     brancas
    -0.56
     inflater
    -0.56
     mourir
    -0.55
     adicionales
    -0.54
    POSITIVE LOGITS
    mathbf
    0.81
    #
    0.79
    textbf
    0.73
    <b>
    0.71
    overset
    0.67
    //
    0.65
     cherchés
    0.64
     ControllerBase
    0.61
     Paglinawan
    0.61
    RegressionTest
    0.60
    Activations Density 0.299%

    No Known Activations