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-2-9B-IT
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 15737
    Prev
    Next
    INDEX
    Explanations

    references to the act of sewing and its related skills

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    sewing

    np_acts-logits-general · gemini-2.0-flash

    sewing by women

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_16k/average_l0_76
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hydrauli
    -0.40
     tatuajes
    -0.37
     mxArray
    -0.35
     Vereine
    -0.34
     pulseras
    -0.34
     AFFAIRS
    -0.33
     escalera
    -0.32
     bandeja
    -0.32
     huella
    -0.32
     tatuagens
    -0.32
    POSITIVE LOGITS
     sewing
    1.45
     sew
    1.33
     sewn
    1.29
     sewed
    1.23
     Sewing
    1.22
    sewing
    1.16
    Sew
    1.16
     Sew
    1.13
    sew
    1.09
     seam
    1.05
    Activations Density 0.118%

    No Known Activations