© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14139
    Prev
    Next
    INDEX
    Explanations

    technical terms and fields related to flight information and airport data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    的发
    -0.34
     печи
    -0.31
    릴
    -0.31
     brinquedos
    -0.30
     rela
    -0.30
     ат
    -0.29
    ContentAsync
    -0.29
     pubblic
    -0.29
     verrez
    -0.29
     metus
    -0.28
    POSITIVE LOGITS
    rungsseite
    0.73
     booking
    0.70
     bookings
    0.68
     Booking
    0.64
     Expedia
    0.62
    Lähteet
    0.58
    Booking
    0.58
     booked
    0.58
     Travel
    0.57
     Wicidata
    0.57
    Activations Density 0.051%

    No Known Activations