© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 3429
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate ongoing actions or situations, particularly involving the word "while."

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

    "while" followed by a pronoun

    np_acts-logits-general · gemini-2.0-flash

    while followed by an ongoing action or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    #+#
    -0.80
     geworden
    -0.58
    ніципалі
    -0.56
    rdı
    -0.51
     Joining
    -0.50
    olyb
    -0.49
     chi̍t
    -0.49
     насељу
    -0.48
    će
    -0.48
    Joining
    -0.48
    POSITIVE LOGITS
     estiver
    0.81
    wijl
    0.81
     sedang
    0.80
    ViewFeatures
    0.74
    กำลัง
    0.73
     Mentre
    0.71
    還在
    0.71
     esteve
    0.71
     đang
    0.71
     preparing
    0.70
    Activations Density 0.253%

    No Known Activations