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. 20-GEMMASCOPE-RES-16K
    6. 8726
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements and specifications in experimental procedures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     متعلقه
    -0.80
    
    -0.76
    WriteAttribute
    -0.75
    AddTagHelper
    -0.74
    /*
    -0.72
    IContainer
    -0.68
    tonsoft
    -0.67
    Билгалдахарш
    -0.66
    Amicalement
    -0.66
    Xna
    -0.65
    POSITIVE LOGITS
    gram
    0.61
     grams
    0.58
     gouttes
    0.57
     mg
    0.56
    mg
    0.56
     drops
    0.56
    grams
    0.55
     milligrams
    0.54
     gram
    0.53
     γρα
    0.53
    Activations Density 0.378%

    No Known Activations