© 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-2-2B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 6944
    Prev
    Next
    INDEX
    Explanations

    the word "that."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    த்தில்
    -0.48
    Bissau
    -0.47
    himo
    -0.47
    gle
    -0.46
    volte
    -0.46
    wieś
    -0.45
     Tempor
    -0.45
    ורי
    -0.44
    empor
    -0.44
     Tela
    -0.43
    POSITIVE LOGITS
    ArgsConstructor
    1.00
    That
    0.99
     estimés
    0.97
     That
    0.94
     daquele
    0.92
    tvguidetime
    0.89
    脚注の使い方
    0.86
    parsedMessage
    0.85
     المعيارى
    0.83
    THAT
    0.83
    Activations Density 0.085%

    No Known Activations