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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11603
    Prev
    Next
    INDEX
    Explanations

    references to sewing and crafting activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     contratto
    -0.31
     Sécurité
    -0.28
     maintien
    -0.28
     disposiciones
    -0.28
     vertrou
    -0.27
     pemer
    -0.27
     bewust
    -0.26
     FetchType
    -0.26
     trăm
    -0.25
     law
    -0.25
    POSITIVE LOGITS
     creations
    0.84
     creativity
    0.79
     artis
    0.77
     artistry
    0.76
     creative
    0.76
     creatively
    0.75
    artistic
    0.75
     handmade
    0.74
     crafts
    0.74
     artistic
    0.74
    Activations Density 0.366%

    No Known Activations