© 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. 28-GEMMASCOPE-RES-16K
    11. 7867
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" in context

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

    the word "while"

    np_acts-logits-general · gemini-2.0-flash

    while clauses / waiting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     resourceCulture
    -0.45
    WebControls
    -0.44
    TagMode
    -0.42
     dô
    -0.37
     siff
    -0.36
    SourceChecksum
    -0.35
    Dès
    -0.35
    ∬
    -0.34
     Dès
    -0.33
    र्फ
    -0.33
    POSITIVE LOGITS
     waiting
    0.61
    WHILE
    0.59
     Enquanto
    0.59
     awaiting
    0.59
     Mientras
    0.57
     bezig
    0.57
    While
    0.57
     While
    0.55
     WHILE
    0.55
    while
    0.53
    Activations Density 0.177%

    No Known Activations