© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 992
    Prev
    Next
    INDEX
    Explanations

    terms related to washing and cleaning processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.82
     pulumi
    -0.79
     reven
    -0.75
     Chwiliwch
    -0.70
    SpringRunner
    -0.65
     تضيفلها
    -0.62
     GenerationType
    -0.62
     Lott
    -0.61
     Dij
    -0.60
    endregion
    -0.58
    POSITIVE LOGITS
     washing
    1.28
     wash
    1.21
     washes
    1.19
     Washing
    1.17
    Washing
    1.16
    Wash
    1.16
     WASH
    1.15
     washed
    1.15
     Wash
    1.10
    washing
    1.09
    Activations Density 0.168%

    No Known Activations