© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 8935
    Prev
    Next
    INDEX
    Explanations

    references to automobiles or auto-related terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -0.72
     tramonto
    -0.71
     kasarigan
    -0.63
    bitat
    -0.62
     noDo
    -0.60
     Réponses
    -0.60
    makeConstraints
    -0.54
    postsleuth
    -0.52
    лтемелер
    -0.51
    Diweddarwch
    -0.51
    POSITIVE LOGITS
     Auto
    1.10
    Auto
    1.09
    auto
    0.97
     auto
    0.96
     AUTO
    0.75
    AUTO
    0.73
     during
    0.59
     Sun
    0.59
    オート
    0.56
     Autos
    0.55
    Activations Density 0.203%

    No Known Activations