© 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. 20-GEMMASCOPE-RES-16K
    11. 4007
    Prev
    Next
    INDEX
    Explanations

    technical terms related to vehicle control and automation

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

    Mouse, keyboard, or touch input

    np_acts-logits-general · gemini-2.0-flash

    input controls and actions

    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
     MeV
    -0.56
     tarn
    -0.55
     Tarn
    -0.53
     stanzas
    -0.52
    akaian
    -0.52
     caroten
    -0.50
     muffler
    -0.50
     Cushman
    -0.50
    fhir
    -0.49
    ⓘ
    -0.48
    POSITIVE LOGITS
     keyboard
    1.28
     Keyboard
    1.11
    Keyboard
    1.03
    keyboard
    0.99
     mouse
    0.97
     buttons
    0.95
     teclado
    0.92
     controls
    0.91
     keyboards
    0.90
     touchpad
    0.89
    Activations Density 0.292%

    No Known Activations