© 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. 24-GEMMASCOPE-RES-16K
    11. 12207
    Prev
    Next
    INDEX
    Explanations

    instances of the word "while" in different contexts

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

    "while" followed by a pronoun or action

    np_acts-logits-general · gemini-2.0-flash

    while followed by gerund

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    them
    -0.56
     stället
    -0.54
     honom
    -0.53
    where
    -0.52
    quelles
    -0.51
     kerana
    -0.48
     senaste
    -0.48
     cómo
    -0.48
    了
    -0.47
     adalah
    -0.47
    POSITIVE LOGITS
     they
    1.35
     simultaneously
    1.19
     still
    1.18
     we
    1.15
     others
    1.08
    still
    1.01
     awaiting
    1.00
     there
    0.99
     also
    0.97
     nahilalakip
    0.93
    Activations Density 0.118%

    No Known Activations