© 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. 3-GEMMASCOPE-RES-16K
    11. 8478
    Prev
    Next
    INDEX
    Explanations

    the word "either"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
     didst
    -0.54
    MemoryWarning
    -0.52
    Géographie
    -0.50
    PyTuple
    -0.50
    TargetException
    -0.50
     contextLoads
    -0.48
    stination
    -0.47
    ComponentModel
    -0.47
    gelopen
    -0.46
    kheim
    -0.45
    POSITIVE LOGITS
     either
    1.67
    either
    1.52
     Either
    1.41
    Either
    1.41
     entweder
    1.27
    要么
    0.95
     enten
    0.94
    (((
    0.89
    ((
    0.88
     либо
    0.77
    Activations Density 0.065%

    No Known Activations