© 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. 9488
    Prev
    Next
    INDEX
    Explanations

    usage of the word "can" in various contexts

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

    "can" followed by a negative word

    np_acts-logits-general · gemini-2.0-flash

    can't or can never

    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
    клопе
    -0.61
    Chham
    -0.57
    ledes
    -0.56
    adays
    -0.55
    alamu
    -0.54
    ритори
    -0.54
    ۜ
    -0.54
    */),
    -0.54
    $',
    -0.53
    Kjelder
    -0.53
    POSITIVE LOGITS
     neither
    0.87
     barely
    0.82
    neither
    0.78
     hardly
    0.75
     only
    0.70
     Neither
    0.67
     never
    0.65
     scarcely
    0.64
     no
    0.63
     nowhere
    0.63
    Activations Density 0.105%

    No Known Activations