© 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. 2-GEMMASCOPE-RES-16K
    11. 8435
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to flavor and taste

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    strix
    -0.37
    舺
    -0.37
     désolés
    -0.36
     Berman
    -0.36
     Underwood
    -0.34
     パスタ
    -0.34
     )$
    -0.34
     Ordin
    -0.34
     ,
    -0.33
     sn
    -0.33
    POSITIVE LOGITS
     taste
    1.32
     tastes
    1.27
     tasted
    1.27
     flavour
    1.27
     flavor
    1.26
    Taste
    1.15
     Taste
    1.14
     tasting
    1.13
    taste
    1.12
     flavours
    1.08
    Activations Density 0.121%

    No Known Activations