© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 734
    Prev
    Next
    INDEX
    Explanations

    Python syntax related to array and data manipulation

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

    "np" or tokens after equals signs

    np_acts-logits-general · gemini-2.0-flash

    numpy array creation

    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
    enschaft
    -0.52
     String
    -0.49
     "
    -0.49
     str
    -0.49
     “
    -0.47
     string
    -0.47
    Strat
    -0.43
    setString
    -0.43
    âu
    -0.42
    ControllerAdvice
    -0.42
    POSITIVE LOGITS
     np
    1.48
    np
    1.45
    rungsseite
    0.89
    torch
    0.74
     torch
    0.72
    Geplaatst
    0.71
    Xna
    0.69
    AntiForgeryToken
    0.69
    hoga
    0.67
     numpy
    0.66
    Activations Density 0.045%

    No Known Activations