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. 0-GEMMASCOPE-RES-16K
    6. 7893
    Prev
    Next
    INDEX
    Explanations

    specific keywords and identifiers related to programming and software development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     whoſe
    -0.61
    urtz
    -0.59
    Tembelea
    -0.58
     ſmall
    -0.55
    acherous
    -0.54
    //*/
    -0.54
     Eſ
    -0.54
     thoſe
    -0.54
    nologue
    -0.53
    endrait
    -0.53
    POSITIVE LOGITS
    AspNetCore
    0.71
     AssemblyProduct
    0.71
    ArrowToggle
    0.57
    +#+#
    0.55
     BorderRadius
    0.55
     createSprite
    0.52
    windowFixed
    0.52
     Lav
    0.52
    次
    0.52
     BoxFit
    0.50
    Activations Density 2.419%

    No Known Activations