© 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. 22-GEMMASCOPE-RES-16K
    11. 2826
    Prev
    Next
    INDEX
    Explanations

    references to taxi or ride-sharing services and related experiences

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

    Taxi or ride-sharing services

    np_acts-logits-general · gemini-2.0-flash

    Uber taxi cab rides

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MemoryWarning
    -0.70
     asics
    -0.51
    ConstraintMaker
    -0.50
    :+:
    -0.50
    viewers
    -0.50
     esternos
    -0.50
    ContentAsync
    -0.49
    antMatchers
    -0.49
    Purch
    -0.48
     smelting
    -0.47
    POSITIVE LOGITS
     ride
    1.33
     Uber
    1.29
     taxi
    1.28
     rides
    1.25
     cab
    1.21
     Taxi
    1.16
    Uber
    1.15
     Rides
    1.15
     Ride
    1.10
     cabs
    1.07
    Activations Density 0.087%

    No Known Activations