© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 10292
    Prev
    Next
    INDEX
    Explanations

    terms related to "driving" or vehicle operation

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

    "driving" and "drive"

    np_acts-logits-general · gemini-2.0-flash

    drive or associated actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ruptcy
    -0.94
     bezeichneter
    -0.83
    Personensuche
    -0.73
     GSC
    -0.73
    XmlAccessorType
    -0.72
     Bourgoin
    -0.70
     Pronto
    -0.70
     (_.
    -0.69
    unkt
    -0.68
     Orton
    -0.67
    POSITIVE LOGITS
     drives
    1.21
     drivers
    1.12
     webdriver
    1.02
     drive
    1.01
     Drives
    0.99
     Drivers
    0.97
     driving
    0.97
     driver
    0.96
     Drive
    0.96
    drives
    0.95
    Activations Density 0.099%

    No Known Activations