© 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. 6-GEMMASCOPE-RES-16K
    6. 11972
    Prev
    Next
    INDEX
    Explanations

    terms related to washing or cleaning actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_6/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_resid_post
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.81
     Normdatei
    -0.77
     Вікіпе
    -0.75
     cương
    -0.75
    tonsoft
    -0.72
    odeficiency
    -0.72
    setPreferred
    -0.71
    spaceBetween
    -0.69
    setOnItem
    -0.69
     AssemblyCulture
    -0.69
    POSITIVE LOGITS
     wash
    1.76
     WASH
    1.74
     washed
    1.72
    Wash
    1.71
     Wash
    1.68
     washing
    1.65
     washes
    1.61
    wash
    1.57
    WASH
    1.48
     Washing
    1.48
    Activations Density 0.033%

    No Known Activations