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. 16-GEMMASCOPE-RES-16K
    6. 3032
    Prev
    Next
    INDEX
    Explanations

    details related to the layout and arrangement of objects or spaces

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Furniture and room items

    np_acts-logits-general · gemini-2.0-flash

    furniture and seating items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     toiture
    -0.54
     igaz
    -0.53
    buquerque
    -0.51
    Roof
    -0.50
    uparrow
    -0.49
    енча
    -0.49
    PackageManager
    -0.48
     tournée
    -0.47
    dibly
    -0.47
    tidal
    -0.47
    POSITIVE LOGITS
     تضيفلها
    0.79
     chairs
    0.78
     stools
    0.72
     chair
    0.71
    chairs
    0.67
     surla
    0.66
     seating
    0.66
     bench
    0.66
     desk
    0.65
     незавершена
    0.65
    Activations Density 0.216%

    No Known Activations