© 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. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 3665
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    36.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specific phrases or terms that relate to professional job descriptions or qualifications

    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
     AssemblyVersion
    -0.39
    Hochspringen
    -0.36
     ffilm
    -0.35
     manual
    -0.35
     Ejercicio
    -0.34
    úrate
    -0.34
     Negra
    -0.33
     eigentlich
    -0.33
    iestety
    -0.33
    ailleurs
    -0.33
    POSITIVE LOGITS
    
    0.55
     propOrder
    0.53
    setVerticalGroup
    0.50
    TemporalType
    0.48
    MessageTagHelper
    0.47
     виправивши
    0.46
     متعلقه
    0.45
    peech
    0.44
    <tfoot>
    0.43
    LookAnd
    0.43
    Activations Density 5.386%

    No Known Activations