© 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. 20-GEMMASCOPE-RES-16K
    11. 856
    Prev
    Next
    INDEX
    Explanations

    terms related to driving and vehicles

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

    "drive" or "driving"

    np_acts-logits-general · gemini-2.0-flash

    drive, driving, and driving-related terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     bezeichneter
    -0.95
    ruptcy
    -0.91
    XmlAccessorType
    -0.74
     relativity
    -0.72
     GSC
    -0.71
     QtGui
    -0.67
     Pronto
    -0.67
     Widgets
    -0.67
     cerebellum
    -0.66
     Blackout
    -0.65
    POSITIVE LOGITS
     drives
    1.00
     drivers
    0.88
     Drives
    0.85
     webdriver
    0.83
     Drivers
    0.81
     Drive
    0.76
    drives
    0.75
     drove
    0.73
     drive
    0.73
     DRIVE
    0.71
    Activations Density 0.081%

    No Known Activations