© 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. 22-GEMMASCOPE-RES-16K
    11. 5307
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and programming constructs

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

    "p" after * or symbols

    np_acts-logits-general · gemini-2.0-flash

    mathematical variable p

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     فريبيس
    -1.00
     дописавши
    -0.86
    IsContent
    -0.81
    RenderAtEndOf
    -0.73
     '\\;'
    -0.73
     виправивши
    -0.69
     Signalez
    -0.69
     bezeichneter
    -0.68
     المعيارى
    -0.65
     otomatig
    -0.64
    POSITIVE LOGITS
     p
    2.29
    p
    2.12
     P
    0.95
    ｐ
    0.92
    P
    0.86
    𝑝
    0.85
     page
    0.76
     प
    0.74
     р
    0.70
    page
    0.68
    Activations Density 0.346%

    No Known Activations