© 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. 3-GEMMASCOPE-RES-16K
    11. 2500
    Prev
    Next
    INDEX
    Explanations

    instances of the word "whether" and its variations

    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
     Millard
    -0.74
     ldc
    -0.62
     Pittman
    -0.62
     cards
    -0.62
     lid
    -0.61
     Pires
    -0.61
    pekt
    -0.60
    瓏
    -0.60
     Lola
    -0.60
    uxley
    -0.59
    POSITIVE LOGITS
     whether
    2.98
    whether
    2.86
     WHETHER
    2.81
     Whether
    2.74
    Whether
    2.67
     apakah
    1.64
    是否
    1.37
    WHE
    1.29
     是否
    1.27
     jestli
    1.24
    Activations Density 0.065%

    No Known Activations