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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 15355
    Prev
    Next
    INDEX
    Explanations

    activities related to household chores and cleaning tasks

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

    cleaning

    np_acts-logits-general · gemini-2.0-flash

    house cleaning

    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
     متعلقه
    -0.69
    WebVitals
    -0.55
    WriteLiteral
    -0.55
    rrggbb
    -0.53
     prescribing
    -0.49
    #
    -0.49
     SwitchCompat
    -0.48
    XtraReports
    -0.48
    prepareStatement
    -0.47
    openzeppelin
    -0.47
    POSITIVE LOGITS
     cleaning
    2.45
     Cleaning
    2.21
    cleaning
    2.13
     cleaned
    2.12
    Cleaning
    2.09
     clean
    2.09
     cleans
    2.07
     cleaner
    2.01
     cleanliness
    2.00
     CLEANING
    1.97
    Activations Density 0.178%

    No Known Activations