© 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. 31-GEMMASCOPE-RES-16K
    11. 4698
    Prev
    Next
    INDEX
    Explanations

    details related to vehicle attributes and features

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

    detailed descriptions of vehicle movements and actions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aboli
    -0.38
    ngdoc
    -0.36
    cora
    -0.36
    gmd
    -0.35
     proie
    -0.34
     abstra
    -0.33
    pasang
    -0.33
    rinfo
    -0.33
    krä
    -0.33
     chor
    -0.33
    POSITIVE LOGITS
     parked
    1.05
     parking
    0.90
     parkir
    0.83
     PARKING
    0.75
     park
    0.75
     Parking
    0.75
     reversing
    0.74
     driveway
    0.73
    parking
    0.72
     estacion
    0.72
    Activations Density 0.252%

    No Known Activations