© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 9430
    Prev
    Next
    INDEX
    Explanations

    regulatory requirements related to pilot licensing and flight operations

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

    after articles (a, an, the)

    np_acts-logits-general · gemini-2.0-flash

    private aircraft and pilots

    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
     ModelExpression
    -0.83
     незавершена
    -0.80
    ंदीखरीदारी
    -0.78
     שוליים
    -0.71
     HttpNotFound
    -0.67
     nonUne
    -0.66
    ⎩
    -0.66
    سطس
    -0.65
    Билгалдахарш
    -0.63
    +#+#
    -0.62
    POSITIVE LOGITS
     private
    0.74
    private
    0.70
     Private
    0.64
    Private
    0.59
     bush
    0.59
     fixed
    0.58
    PRIVATE
    0.57
     PRIVATE
    0.54
     Fixed
    0.52
     ul
    0.51
    Activations Density 0.149%

    No Known Activations