Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114901
    Prev
    Next
    INDEX
    Explanations

    terminology and structure related to test cases in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    }{*}{
    -0.52
    closedir
    -0.47
    //
    -0.47
     влади
    -0.44
     שוליים
    -0.42
    _
    
    -0.41
    enumi
    -0.40
    めでとう
    -0.40
    uinal
    -0.40
    iyaki
    -0.39
    POSITIVE LOGITS
     TestCase
    1.77
    TestCase
    1.71
     testCase
    1.09
    testcase
    1.09
    testCase
    1.00
     testcase
    0.96
     XCTest
    0.81
     AssemblyTitle
    0.72
    TestMethod
    0.71
    TestBase
    0.69
    Activations Density 0.003%

    No Known Activations