© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 22094
    Prev
    Next
    INDEX
    Explanations

    mentions of specific car models and their characteristics

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

    cars and car manufacturers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Athletics
    -0.36
     hike
    -0.35
    grid
    -0.34
     hikes
    -0.34
    Grid
    -0.33
    Athletics
    -0.33
     yük
    -0.32
     hek
    -0.31
     Grid
    -0.31
    กร
    -0.31
    POSITIVE LOGITS
     limousine
    0.90
     limo
    0.76
     Cadillac
    0.75
     chauffe
    0.74
     lim
    0.74
     chauffeur
    0.74
    limo
    0.66
     chauff
    0.66
     Rolls
    0.60
    illac
    0.58
    Activations Density 0.048%

    No Known Activations