Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 13430
    Prev
    Next
    INDEX
    Explanations

    references to sewing and its relevance across generations

    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
     carpets
    -0.54
     tights
    -0.53
    NonQuery
    -0.52
     StringTokenizer
    -0.52
     FRP
    -0.52
    istán
    -0.51
     Vane
    -0.50
     flyknit
    -0.50
     memer
    -0.49
     glab
    -0.49
    POSITIVE LOGITS
    DebuggerNonUser
    0.78
    findpost
    0.72
    Sew
    0.71
     iron
    0.67
     skär
    0.67
     Iron
    0.66
     hierro
    0.65
     sewing
    0.64
    Iron
    0.64
     Sew
    0.64
    Activations Density 0.194%

    No Known Activations