© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 4015
    Prev
    Next
    INDEX
    Explanations

    concepts related to wave functions in quantum physics

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

    "wave" followed by a word indicating function/property

    np_acts-logits-general · gemini-2.0-flash

    wave function

    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
     Chwiliwch
    -0.57
     uLocal
    -0.54
    ┗
    -0.53
    helf
    -0.51
    Muss
    -0.49
    CloseOperation
    -0.48
     occident
    -0.47
     Airs
    -0.47
    misu
    -0.45
     kalan
    -0.45
    POSITIVE LOGITS
     goodbye
    0.69
    guides
    0.68
    front
    0.68
    álise
    0.63
    editForm
    0.62
     Phenomena
    0.61
    XtraGrid
    0.61
     Riders
    0.60
    kháu
    0.59
     lengths
    0.59
    Activations Density 0.183%

    No Known Activations