© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 11535
    Prev
    Next
    INDEX
    Explanations

    references to essential oils and their properties

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

    names of herbs, spices, and botanical plants.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi

    culinary and medicinal herbs and plant names.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CGContext
    -0.42
     toti
    -0.40
    PushMatrix
    -0.38
    COLN
    -0.36
    sofá
    -0.36
    NSObject
    -0.34
    älter
    -0.34
     paraître
    -0.34
    pyx
    -0.34
     étoient
    -0.34
    POSITIVE LOGITS
     herbs
    0.98
     herb
    0.96
     aromatic
    0.88
     thyme
    0.86
     lavender
    0.84
     Herbs
    0.81
     rosemary
    0.80
     herbal
    0.80
     aromatherapy
    0.79
     arom
    0.79
    Activations Density 0.146%

    No Known Activations