© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 86074
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" and contexts involving dual or comparative situations

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

    while followed by location or state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    SequentialGroup
    -0.57
    Hentet
    -0.57
     disambiguazione
    -0.53
    TagMode
    -0.51
    Personensuche
    -0.48
     médié
    -0.47
     מוכ
    -0.46
    contentLoaded
    -0.44
    Diweddarwch
    -0.44
    writerow
    -0.43
    POSITIVE LOGITS
    while
    0.67
    WHILE
    0.66
     while
    0.66
    While
    0.65
     While
    0.63
     enquanto
    0.57
     동안
    0.56
     WHILE
    0.56
     Enquanto
    0.54
     Mientras
    0.54
    Activations Density 0.035%

    No Known Activations