Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73488
    Prev
    Next
    INDEX
    Explanations

    phrases related to ordering or serving food and drinks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SpringBootTest
    -0.66
    Geplaatst
    -0.59
    XmlType
    -0.59
    queryInterface
    -0.54
    kháu
    -0.54
    TestTools
    -0.52
     Numerade
    -0.52
     CGSize
    -0.51
    Datuak
    -0.50
    offsetof
    -0.50
    POSITIVE LOGITS
     sit
    0.37
     שוליים
    0.34
     dining
    0.34
     entertaining
    0.33
     sitting
    0.32
     waiter
    0.31
     Dining
    0.29
    Fordítás
    0.29
    kenalkan
    0.29
     coffee
    0.28
    Activations Density 0.006%

    No Known Activations