© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4024
    Prev
    Next
    INDEX
    Explanations

    concepts related to washing, cleaning, and laundering

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

    washing

    np_acts-logits-general · gemini-2.0-flash

    wash or washed away

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    bootstrapcdn
    -0.68
    CPtr
    -0.65
     Litt
    -0.63
    OwnProperty
    -0.62
    contentLoaded
    -0.62
    Sitio
    -0.61
    
    -0.59
     Maje
    -0.59
    onedDateTime
    -0.59
    ränkt
    -0.57
    POSITIVE LOGITS
     Washburn
    0.84
     WASH
    0.80
    Wash
    0.75
     Wash
    0.75
    WASH
    0.70
    Washing
    0.69
     Washing
    0.69
     washed
    0.69
     washes
    0.69
     washing
    0.69
    Activations Density 0.077%

    No Known Activations