© 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 - 65k
    9. 20-GEMMASCOPE-RES-65K
    11. 415
    Prev
    Next
    INDEX
    Explanations

    references to the NumPy library and its usage in code

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

    Python import statements related to the NumPy library

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

    data techniques and programming

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_65k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     st
    -0.57
     grazia
    -0.56
    <strong>
    -0.49
    <eos>
    -0.46
    addto
    -0.46
     будешь
    -0.45
     lontano
    -0.44
     Bowden
    -0.43
     tarik
    -0.43
     compagn
    -0.43
    POSITIVE LOGITS
     numpy
    1.35
    InputTagHelper
    1.06
    aarrggbb
    1.02
    AccessorTable
    0.88
    numpy
    0.88
     ProtoMessage
    0.83
    expandindo
    0.82
    PyExc
    0.80
    pyplot
    0.80
     MotionEvent
    0.80
    Activations Density 0.002%

    No Known Activations