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. 9164
    Prev
    Next
    INDEX
    Explanations

    references to fabric and materials used in sewing

    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
    SuppressMessage
    -0.62
    WarningLevel
    -0.61
     MenuView
    -0.57
    الإنجليزية
    -0.56
    AndEndTag
    -0.53
    avajillas
    -0.52
     pleaſure
    -0.51
    teger
    -0.50
    lück
    -0.49
    xDB
    -0.49
    POSITIVE LOGITS
     fabrics
    1.54
     fabric
    1.53
     textile
    1.37
     Fabrics
    1.29
     textiles
    1.26
     Fabric
    1.26
     cotton
    1.25
     sewn
    1.24
     embroidered
    1.22
     Textile
    1.21
    Activations Density 0.511%

    No Known Activations