© 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-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11236
    Prev
    Next
    INDEX
    Explanations

    elements related to food reviews, particularly descriptions of meals and their quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ceğine
    -0.54
     hessen
    -0.51
     niyang
    -0.50
    elemField
    -0.48
    GTCX
    -0.47
    topatho
    -0.47
    zellan
    -0.45
    SharedDtor
    -0.45
    Trayectoria
    -0.45
     Metacritic
    -0.45
    POSITIVE LOGITS
     expat
    0.77
     locals
    0.77
     hostels
    0.69
     foreigners
    0.69
     tourist
    0.67
     hostel
    0.66
     homestay
    0.63
     guesthouse
    0.62
     Locals
    0.62
     foreigner
    0.61
    Activations Density 0.342%

    No Known Activations