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. 15-GEMMASCOPE-RES-16K
    6. 2438
    Prev
    Next
    INDEX
    Explanations

    instances of the word "quad" indicating mathematical or scientific equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/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.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CreateTagHelper
    -0.80
     ponta
    -0.77
     PLE
    -0.72
     fry
    -0.72
    LikeLike
    -0.72
    runApp
    -0.70
     Мексичка
    -0.69
    ={({
    -0.69
     Twe
    -0.67
    appeal
    -0.67
    POSITIVE LOGITS
    quad
    1.24
    riceps
    0.76
     quad
    0.74
    ctive
    0.68
     quadrant
    0.65
     quads
    0.65
     Meiji
    0.64
     poveznice
    0.64
      
    0.63
    Ỉ
    0.62
    Activations Density 0.062%

    No Known Activations