© 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. 4002
    Prev
    Next
    INDEX
    Explanations

    technical terms and procedural descriptions related to experiments, data analysis, and scientific research methodologies

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

    Abbreviations "SW", "RW", "DW", and "WW"

    np_acts-logits-general · gemini-2.0-flash

    swanson, swaziland, swig

    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
     Pape
    -0.58
     Carrington
    -0.56
    tagHelperRunner
    -0.56
     Vege
    -0.56
     Gabe
    -0.54
     Harrington
    -0.54
    Vege
    -0.54
    Deli
    -0.53
     Sabina
    -0.53
    Gabe
    -0.52
    POSITIVE LOGITS
     SW
    1.97
     Sw
    1.94
    Sw
    1.85
    SW
    1.79
    sw
    1.66
     sw
    1.63
     Swanson
    1.48
     BW
    1.42
     Swan
    1.36
     MW
    1.36
    Activations Density 0.432%

    No Known Activations