© 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. 11764
    Prev
    Next
    INDEX
    Explanations

    technical terms related to surface preparation and treatment processes

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

    Surface abrasion or smoothing

    np_acts-logits-general · gemini-2.0-flash

    surface smoothing and abrasive processing

    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
     Darm
    -0.56
     الحره
    -0.54
    schild
    -0.51
     consultato
    -0.51
    inerja
    -0.49
     вікі
    -0.49
    ásticas
    -0.48
    reathe
    -0.48
    thren
    -0.48
    zweig
    -0.48
    POSITIVE LOGITS
     sandpaper
    1.19
     sanding
    1.15
     polishing
    1.09
     sanded
    1.02
     abrasive
    0.94
     grinding
    0.93
     smoothing
    0.91
    Sand
    0.89
     polish
    0.89
     Sand
    0.88
    Activations Density 0.217%

    No Known Activations