© 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. 38-GEMMASCOPE-RES-16K
    11. 15241
    Prev
    Next
    INDEX
    Explanations

    questions related to airline operations and industry dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Descripció
    -0.38
     zade
    -0.37
    rawQuery
    -0.35
    UnusedPrivate
    -0.34
    ukkig
    -0.34
    hyrchwyd
    -0.33
     bénévol
    -0.33
    #+#
    -0.32
     Exacts
    -0.32
    cemment
    -0.32
    POSITIVE LOGITS
     airline
    2.06
     airlines
    2.02
     flight
    1.99
     aviation
    1.93
     airport
    1.85
     aircraft
    1.84
     Flight
    1.80
     Airline
    1.78
     airplane
    1.78
     flights
    1.77
    Activations Density 0.439%

    No Known Activations