© 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. 11493
    Prev
    Next
    INDEX
    Explanations

    references to cars and automotive-related terms

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

    the word "car" in various contexts and compound words.

    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
    y
    -0.47
    es
    -0.37
     oppos
    -0.35
    te
    -0.34
     flé
    -0.34
    י
    -0.34
    Segoe
    -0.33
    est
    -0.33
     Chambers
    -0.32
    亏
    -0.32
    POSITIVE LOGITS
     autorytatywna
    0.91
     car
    0.75
    🚗
    0.72
     automobile
    0.71
     חיצוניים
    0.70
     Automobile
    0.69
    Automobile
    0.68
    automobile
    0.67
     dealerships
    0.67
     للمعارف
    0.66
    Activations Density 0.088%

    No Known Activations