© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12986
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives related to fragrance and beauty

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

    scents and smells

    np_acts-logits-general · gemini-2.0-flash

    signature scent

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.81
     pédagog
    -0.70
    Filmografia
    -0.67
    UseVisualStyle
    -0.58
     Hobson
    -0.56
    GraphicsUnit
    -0.56
    enumerable
    -0.53
     pédagogique
    -0.53
     quæ
    -0.52
     graphiques
    -0.51
    POSITIVE LOGITS
     scent
    1.00
     fragrance
    0.94
     scents
    0.90
     fragrances
    0.82
     smelling
    0.82
     perfume
    0.77
     accords
    0.76
     Eau
    0.74
     smells
    0.74
     Scent
    0.72
    Activations Density 0.035%

    No Known Activations