© 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. 33-GEMMASCOPE-RES-16K
    11. 10421
    Prev
    Next
    INDEX
    Explanations

    phrases indicating confusion or a desire for clarity in understanding complex subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.43
     EconPapers
    -0.40
     pazi
    -0.34
    Datuak
    -0.32
    announce
    -0.30
    viewBox
    -0.28
     وصلة
    -0.28
    jungan
    -0.28
    anaf
    -0.27
     rynku
    -0.27
    POSITIVE LOGITS
     understanding
    3.13
     understand
    2.97
    understanding
    2.80
     understood
    2.77
     Understanding
    2.72
     understands
    2.69
    Understanding
    2.61
    understand
    2.59
     Understand
    2.56
    Understand
    2.52
    Activations Density 0.788%

    No Known Activations