© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 1812
    Prev
    Next
    INDEX
    Explanations

    features related to vehicle safety and visibility technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.49
     AssemblyTitle
    -0.48
    Datuak
    -0.46
     tartalomajánló
    -0.43
    ContentAsync
    -0.38
     relógio
    -0.38
    ieteur
    -0.37
     meisjes
    -0.34
     /\.(
    -0.34
    dotenv
    -0.34
    POSITIVE LOGITS
     lane
    0.86
     Lane
    0.77
     collision
    0.75
    Lane
    0.73
     braking
    0.70
     occupant
    0.69
     Collision
    0.68
     crash
    0.64
    lane
    0.63
     roadway
    0.63
    Activations Density 0.454%

    No Known Activations