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-2-9B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 272
    Prev
    Next
    INDEX
    Explanations

    references to pixel coordinates and spatial data in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Thacker
    -0.34
    Conclusie
    -0.33
     Calderón
    -0.33
     Acción
    -0.33
     ต่อ
    -0.33
     preliminar
    -0.32
     Alfaro
    -0.32
     sujets
    -0.32
    BackStack
    -0.31
    Action
    -0.31
    POSITIVE LOGITS
     Position
    1.02
     coordinates
    1.02
     Coordinates
    0.99
     coords
    0.98
    Position
    0.98
     POSITION
    0.95
     position
    0.95
     Positions
    0.92
    坐标
    0.91
    position
    0.90
    Activations Density 0.244%

    No Known Activations