© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 1282
    Prev
    Next
    INDEX
    Explanations

    expressions of taste and flavor related to food

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

    expressions related to negative sensory experiences, particularly taste

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

    desscribing flavors and tastes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTS
    -0.65
    GEBURTSDATUM
    -0.61
     Perseus
    -0.52
     SUDOC
    -0.51
     فريبيس
    -0.49
     diligen
    -0.47
    раздо
    -0.46
    انجليز
    -0.46
    Injectable
    -0.46
    হ
    -0.44
    POSITIVE LOGITS
     taste
    2.69
     tastes
    2.40
     tasted
    2.23
    taste
    2.21
     Taste
    2.11
    Taste
    2.04
     flavor
    2.02
     tasting
    1.96
     flavour
    1.91
     flavors
    1.86
    Activations Density 0.161%

    No Known Activations