© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 2167
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" in various contexts

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

    the word "while" and the grammatical context around it.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 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
    ECU
    -0.47
     fédé
    -0.46
     sociaux
    -0.45
     médicale
    -0.43
    AccountNumber
    -0.42
     Tatsache
    -0.42
    ECD
    -0.42
     énergétique
    -0.41
     vétérina
    -0.41
    SSP
    -0.41
    POSITIVE LOGITS
    while
    1.12
     while
    1.09
     WHILE
    1.08
    WHILE
    1.04
    While
    0.98
     While
    0.96
     Mentre
    0.92
     Enquanto
    0.91
    mientras
    0.89
    Mientras
    0.88
    Activations Density 0.067%

    No Known Activations