© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 459
    Prev
    Next
    INDEX
    Explanations

    details related to hospitality and accommodation features

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

    near amenities or accommodations

    np_acts-logits-general · gemini-2.0-flash

    hotel and its amenities

    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-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    Autoritní
    -0.57
     bénévoles
    -0.52
     hemma
    -0.48
    WebServlet
    -0.48
    Купить
    -0.47
     paroisse
    -0.46
     leçon
    -0.46
     ensino
    -0.45
     isKindOfClass
    -0.43
     bancos
    -0.41
    POSITIVE LOGITS
     hotel
    1.30
     guests
    1.15
    hotel
    1.09
    Hotel
    1.06
     Hotel
    1.05
     minibar
    1.05
     breakfast
    1.03
     hote
    1.01
     concierge
    1.01
     Guests
    0.99
    Activations Density 0.096%

    No Known Activations