© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 7988
    Prev
    Next
    INDEX
    Explanations

    terms related to health and beauty products, particularly those linked to chemical compositions and biological interactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beginnetje
    -0.58
    KommentareTeilen
    -0.42
    corazón
    -0.41
     NSCoder
    -0.41
     cerveau
    -0.40
    Autoritní
    -0.39
     brain
    -0.38
     विश्वसनीयता
    -0.37
    Lähteet
    -0.37
     RouterModule
    -0.36
    POSITIVE LOGITS
     skincare
    1.29
     cosmetics
    1.29
     Cosmetics
    1.28
     Skincare
    1.23
     cosmetic
    1.22
     Cosmetic
    1.16
    Beauty
    1.14
     Beauty
    1.14
     acne
    1.11
     lipstick
    1.10
    Activations Density 1.878%

    No Known Activations