© 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-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 93678
    Prev
    Next
    INDEX
    Explanations

    expect statements in testing frameworks

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

    initiate expect assertions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     queſta
    -1.04
    transQ
    -0.75
    IsMutable
    -0.73
    Tikang
    -0.72
     kaarangay
    -0.72
    rrggbb
    -0.71
     Wikimedijinoj
    -0.67
    uxxxx
    -0.63
     للاسماء
    -0.63
    parsedMessage
    -0.63
    POSITIVE LOGITS
    expect
    0.77
    assertThat
    0.60
    hamcrest
    0.42
    Expect
    0.41
     psiqui
    0.37
     expect
    0.37
     Expect
    0.36
    ędz
    0.36
     espé
    0.36
     Haben
    0.35
    Activations Density 0.005%

    No Known Activations