© 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. 22-GEMMASCOPE-RES-16K
    6. 9174
    Prev
    Next
    INDEX
    Explanations

    references to essential oils and their properties

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

    Essential oils and aromatherapy

    np_acts-logits-general · gemini-2.0-flash

    lavender oils

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.81
     مرئيه
    -0.66
     ujednoznacz
    -0.59
     '\\;'
    -0.57
    ViewFeatures
    -0.57
     Italijanski
    -0.56
    таратура
    -0.55
     noDo
    -0.54
    RenderAtEndOf
    -0.54
    :^(
    -0.53
    POSITIVE LOGITS
     diffuser
    0.93
     aromatherapy
    0.85
     Lavender
    0.83
     lavender
    0.79
     Diff
    0.77
     Arom
    0.75
     diff
    0.74
    Lavender
    0.72
     oils
    0.72
     arom
    0.72
    Activations Density 0.064%

    No Known Activations