© 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 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. 14832
    Prev
    Next
    INDEX
    Explanations

    expect statements and their assertions in a testing framework

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

    Followed by parentheses or "toBe" in tests

    np_acts-logits-general · gemini-2.0-flash

    expectations in tests

    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
    InitVars
    -0.89
    Хьажоргаш
    -0.85
    DebuggerNonUser
    -0.81
    -------------</
    -0.78
    principalColumn
    -0.78
     EconPapers
    -0.73
     Bioaccumulative
    -0.70
     tartalomajánló
    -0.68
     otomatig
    -0.68
     beginnetje
    -0.66
    POSITIVE LOGITS
    assertThat
    0.57
    dza
    0.50
    ποι
    0.49
    itzer
    0.48
    êle
    0.48
     jähr
    0.47
     Eus
    0.47
    choon
    0.46
    expect
    0.45
    (()
    0.45
    Activations Density 0.029%

    No Known Activations