© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 9603
    Prev
    Next
    INDEX
    Explanations

    technical terms and components related to machinery and manufacturing processes

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

    Printing/manufacturing process: reels, magazines, assemblers

    np_acts-logits-general · gemini-2.0-flash

    feeding and take-up reels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     akar
    -0.59
     onCreateView
    -0.55
    Izvori
    -0.50
    gste
    -0.50
     murs
    -0.50
     grout
    -0.50
    Sant
    -0.50
     Sumter
    -0.49
     covalent
    -0.48
     transistors
    -0.48
    POSITIVE LOGITS
     feed
    0.87
     feeding
    0.85
     rollers
    0.84
    Feed
    0.81
     roller
    0.80
    feed
    0.79
     Feed
    0.78
     roll
    0.77
     feeder
    0.76
     Feeding
    0.75
    Activations Density 0.585%

    No Known Activations