© 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. 20-GEMMASCOPE-RES-16K
    11. 5699
    Prev
    Next
    INDEX
    Explanations

    terms related to cleanliness and cleaning processes

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

    "clean" or its variations

    np_acts-logits-general · gemini-2.0-flash

    cleanliness and related actions

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     AssemblyCulture
    -0.90
    bootstrapcdn
    -0.87
     esternos
    -0.86
     Baillargeon
    -0.82
    __":
    -0.81
    ServletException
    -0.79
    AndEndTag
    -0.77
     Roskov
    -0.72
     EconPapers
    -0.72
    __':
    -0.72
    POSITIVE LOGITS
    liness
    0.73
     sweep
    0.72
     Clean
    0.69
     cut
    0.66
     CLEAN
    0.65
     cleans
    0.65
     slate
    0.62
     up
    0.60
    Sweep
    0.58
     Sweep
    0.57
    Activations Density 0.082%

    No Known Activations