© 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. 31-GEMMASCOPE-RES-16K
    11. 10707
    Prev
    Next
    INDEX
    Explanations

    architectural and lodging details in travel contexts

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

    travel and hospitality-related content, particularly hotel names, booking information, and accommodation descriptions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ukone
    -0.34
    🟤
    -0.33
    łecz
    -0.33
    greenrobot
    -0.30
    toHaveBeenCalled
    -0.30
    AppMethodBeat
    -0.29
    Personendaten
    -0.29
     Auftrag
    -0.29
     مؤرشف
    -0.29
    Garonne
    -0.28
    POSITIVE LOGITS
     hotel
    2.31
     hotels
    2.11
     Hotel
    2.06
    hotel
    1.95
    Hotel
    1.94
     Hotels
    1.88
     HOTEL
    1.84
     motel
    1.82
    Hotels
    1.78
     hotell
    1.77
    Activations Density 0.219%

    No Known Activations