© 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. 8493
    Prev
    Next
    INDEX
    Explanations

    terms related to "py" or variations of "py"

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

    "Py" followed by other letters

    np_acts-logits-general · gemini-2.0-flash

    words starting with py

    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
    новниш
    -0.78
    lapsingToolbar
    -0.72
    interopRequire
    -0.72
    Tembelea
    -0.62
    frow
    -0.61
     alignItems
    -0.60
    ReactDOM
    -0.59
     المعيارى
    -0.59
     Becher
    -0.59
     InputDecoration
    -0.58
    POSITIVE LOGITS
     Py
    0.88
     py
    0.74
    Py
    0.69
     PyObject
    0.63
     PY
    0.63
    thag
    0.52
     pyrite
    0.51
    PY
    0.50
    tanie
    0.50
     pym
    0.46
    Activations Density 0.119%

    No Known Activations