© 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. 16-GEMMASCOPE-RES-16K
    11. 7163
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notations related to Lévy processes

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

    Mathematical or symbolic notation

    np_acts-logits-general · gemini-2.0-flash

    integrals and probability notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.64
     himſelf
    -0.62
     muſt
    -0.58
    ſelf
    -0.53
     Monfieur
    -0.52
     itself
    -0.52
     myſelf
    -0.51
     Beſ
    -0.51
    archiviato
    -0.51
     Jefus
    -0.51
    POSITIVE LOGITS
    Referències
    0.68
     Meksiku
    0.59
    міністра
    0.57
     esternos
    0.56
    帖最后由
    0.56
    uarts
    0.55
    kespea
    0.55
    ]--;
    0.54
    Przypisy
    0.54
    UVWXYZ
    0.53
    Activations Density 1.087%

    No Known Activations