© 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. 14929
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation related to statistical models

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

    Mathematical notation with subscripts and superscripts

    np_acts-logits-general · gemini-2.0-flash

    $N, n$ dimensions

    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
    Przypisy
    -0.78
    httphttps
    -0.69
     дописавши
    -0.65
     незавершена
    -0.64
    Lähteet
    -0.58
     EconPapers
    -0.57
     שוליים
    -0.56
     saites
    -0.56
     /\.(
    -0.55
    contentLoaded
    -0.55
    POSITIVE LOGITS
    N
    0.84
     n
    0.82
     N
    0.77
    n
    0.75
     dimension
    0.63
    ｎ
    0.60
    Dimension
    0.59
     m
    0.57
     dimensionality
    0.57
    m
    0.57
    Activations Density 2.392%

    No Known Activations