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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 4899
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    55.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    elements related to unit testing and test case structures

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    pyvene/gemma-reft-r1-9b-it-res/l20
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCulture
    -0.53
     Italijanski
    -0.53
    WriteTagHelper
    -0.52
    EndContext
    -0.42
    ChildScrollView
    -0.41
     zijne
    -0.40
     Empfehlung
    -0.40
     LayoutInflater
    -0.39
    Zunanje
    -0.38
     Inscrivez
    -0.38
    POSITIVE LOGITS
     test
    0.62
     Test
    0.56
    TestCase
    0.54
    test
    0.54
     tester
    0.53
     tests
    0.53
     TEST
    0.52
    getTest
    0.52
     TestCase
    0.52
     testing
    0.52
    Activations Density 0.027%

    No Known Activations