© 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-2-9B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 767
    Prev
    Next
    INDEX
    Explanations

    phrases beginning with "whether" that introduce conditional questions or considerations

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

    the word "whether", especially in the context of raising hypothetical scenarios or making conditional statements.

    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
     Palis
    -0.60
    fileID
    -0.60
     Sanford
    -0.57
     Fu
    -0.54
    !*\
    -0.54
     fc
    -0.54
    XG
    -0.54
     fú
    -0.53
     Danilo
    -0.53
     KPK
    -0.52
    POSITIVE LOGITS
     WHETHER
    0.99
    whether
    0.93
     whether
    0.90
     Whether
    0.79
    Whether
    0.77
     betweenstory
    0.67
    eramente
    0.60
     recomendamos
    0.55
    hombres
    0.53
    weder
    0.52
    Activations Density 0.070%

    No Known Activations