© 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. 20-GEMMASCOPE-RES-16K
    11. 16158
    Prev
    Next
    INDEX
    Explanations

    technical terms and error messages related to Python and Django programming

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

    Python-related file paths or libraries

    np_acts-logits-general · gemini-2.0-flash

    Python package installation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Heber
    -0.64
    mappedBy
    -0.58
    icali
    -0.56
     jScrollPane
    -0.56
    estroyer
    -0.52
    Suara
    -0.52
     estekak
    -0.52
    fromnode
    -0.51
    VAO
    -0.51
    limus
    -0.51
    POSITIVE LOGITS
     Py
    0.83
     Python
    0.77
    Py
    0.74
     python
    0.72
    Python
    0.70
     py
    0.69
     PY
    0.68
    django
    0.67
    python
    0.66
    PYX
    0.65
    Activations Density 0.412%

    No Known Activations