© 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. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 2390
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    questions and sentences with a significant level of inquiry or uncertainty

    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
    caloosa
    -0.42
    anair
    -0.38
    bootstrapcdn
    -0.38
     resistive
    -0.36
    __).
    -0.36
     technically
    -0.35
     legisl
    -0.35
     electrically
    -0.34
    WithMany
    -0.34
     insulator
    -0.34
    POSITIVE LOGITS
    SourceChecksum
    0.47
    geslacht
    0.44
     wondered
    0.43
    ClientSize
    0.41
    NOPQRST
    0.41
    addCriterion
    0.41
     bezeichneter
    0.41
    InstrumentedTest
    0.40
     CreateTagHelper
    0.40
     שוליים
    0.39
    Activations Density 0.000%

    No Known Activations