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. 8958
    Prev
    Next
    INDEX
    Explanations

    topics related to food, fashion, and travel experiences

    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
     ainfi
    -0.71
     plufieurs
    -0.65
     enfans
    -0.64
     épis
    -0.62
     barnen
    -0.62
     stället
    -0.60
     auffi
    -0.60
     varandra
    -0.59
    IMPORTED
    -0.59
     générations
    -0.56
    POSITIVE LOGITS
     stuff
    1.09
     thing
    0.89
     matters
    0.78
     things
    0.75
     issues
    0.73
     shenanigans
    0.72
     woes
    0.71
     thingy
    0.69
     shit
    0.68
     stuffs
    0.68
    Activations Density 0.567%

    No Known Activations