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. 13-GEMMASCOPE-RES-16K
    6. 656
    Prev
    Next
    INDEX
    Explanations

    references to individuals and their roles or accomplishments within a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     محفوظة
    -0.62
     chi̍t
    -0.61
     restTemplate
    -0.61
    XmlAccessType
    -0.61
     Chancery
    -0.59
     Gild
    -0.59
    ypep
    -0.59
     Hogarth
    -0.57
     edelstahl
    -0.57
    InputTagHelper
    -0.57
    POSITIVE LOGITS
     sebagai
    0.53
     as
    0.53
    obach
    0.49
    新たに
    0.46
    Act
    0.44
    作為
    0.44
     instead
    0.43
     jako
    0.43
     gekozen
    0.43
     criterio
    0.41
    Activations Density 0.372%

    No Known Activations