Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 1-GEMMASCOPE-RES-16K
    6. 13487
    Prev
    Next
    INDEX
    Explanations

    specific technical terms and components related to programming and data processing

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -0.94
    RenderAtEndOf
    -0.90
     nahilalakip
    -0.83
     ModelExpression
    -0.80
     المعيارى
    -0.77
     שוליים
    -0.75
     Pompey
    -0.72
    StoryboardSegue
    -0.71
     Exactos
    -0.71
    énieurs
    -0.71
    POSITIVE LOGITS
     in
    0.50
    LayoutInflater
    0.48
     samme
    0.47
     podľa
    0.45
    
    0.45
     forme
    0.45
     kil
    0.44
    łbym
    0.44
     tartış
    0.43
    magnet
    0.43
    Activations Density 2.285%

    No Known Activations