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. 24-GEMMASCOPE-RES-131K
    6. 928
    Prev
    Next
    INDEX
    Explanations

    phrases related to planning and organizing travel experiences

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

    travel itinerary

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     entretien
    -0.56
    queryInterface
    -0.49
     fonctionnement
    -0.48
     TextAppearance
    -0.44
    #
    -0.44
     čierna
    -0.43
     miniaturka
    -0.43
     gebruikers
    -0.43
    GIVEREF
    -0.42
     ERSITY
    -0.42
    POSITIVE LOGITS
     itinerary
    0.73
     Itinerary
    0.69
     itineraries
    0.68
     travel
    0.58
     tour
    0.56
    Itinerary
    0.54
     tours
    0.51
     sightseeing
    0.51
     Travel
    0.50
    Grath
    0.50
    Activations Density 0.020%

    No Known Activations