© 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 - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10645
    Prev
    Next
    INDEX
    Explanations

    instances of the term "auto" or variations of it in programming contexts

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

    Code involving the keyword "auto"

    np_acts-logits-general · gemini-2.0-flash

    auto keyword or prefix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Regionen
    -0.47
     Comprometido
    -0.47
    expliquer
    -0.43
     Inseln
    -0.43
     Kassen
    -0.43
     promocional
    -0.42
     voici
    -0.42
     escenarios
    -0.41
     condomínio
    -0.41
     verdieping
    -0.41
    POSITIVE LOGITS
     auto
    3.08
     Auto
    2.91
    auto
    2.86
    Auto
    2.83
     AUTO
    2.64
    AUTO
    2.39
     autos
    1.94
     авто
    1.85
    setAuto
    1.84
    オート
    1.82
    Activations Density 0.079%

    No Known Activations