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. 11-GEMMASCOPE-RES-16K
    6. 5703
    Prev
    Next
    INDEX
    Explanations

    code related to instantiating and managing objects and classes, specifically in a programming context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EnableWeb
    -0.62
    jspx
    -0.50
     hy
    -0.45
    ggings
    -0.45
    ibase
    -0.45
     
    -0.44
     yn
    -0.42
    ặc
    -0.41
    RequiresApi
    -0.41
     plat
    -0.41
    POSITIVE LOGITS
    StoryboardSegue
    0.74
    ArgsConstructor
    0.71
     complètes
    0.67
     pitié
    0.67
    addContainerGap
    0.66
     bağlantılar
    0.65
    الحياه
    0.62
    MLLoader
    0.61
     őket
    0.60
    principalColumn
    0.59
    Activations Density 0.213%

    No Known Activations