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. 460
    Prev
    Next
    INDEX
    Explanations

    dimensions related to width and height in a layout or graphical context

    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
    ⓧ
    -0.92
     ostavi
    -0.85
     snippetHide
    -0.77
     referenties
    -0.74
     @"/
    -0.74
    msgTypes
    -0.72
    MessageTagHelper
    -0.71
    SourceChecksum
    -0.70
    цездатний
    -0.69
     وتسجيلات
    -0.66
    POSITIVE LOGITS
     width
    1.76
    width
    1.59
     Width
    1.46
    Width
    1.35
     WIDTH
    1.18
     length
    1.16
     widths
    1.14
    WIDTH
    1.11
     largeur
    1.02
    height
    0.99
    Activations Density 0.097%

    No Known Activations