© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2528
    Prev
    Next
    INDEX
    Explanations

    references to test cases and testing procedures in programming or software development

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

    "test" and related forms

    np_acts-logits-general · gemini-2.0-flash

    test context

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
    fromCharCode
    -0.71
     femininas
    -0.69
     autorytatywna
    -0.66
    ourcen
    -0.63
     corporativa
    -0.62
     dinheiro
    -0.61
    randomUUID
    -0.60
     manières
    -0.60
    companyname
    -0.59
    Coordenadas
    -0.59
    POSITIVE LOGITS
     test
    1.45
     Test
    1.41
    test
    1.34
    Test
    1.30
     TEST
    1.16
     tests
    1.14
     Tests
    1.09
     testing
    1.08
    TEST
    0.99
     tested
    0.98
    Activations Density 0.160%

    No Known Activations