© 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. 1821
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    66
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    concepts related to analysis and evaluation

    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
     Wikimedijinoj
    -0.70
    WriteTagHelper
    -0.70
    :✨
    -0.67
    Personendaten
    -0.67
     $_(
    -0.66
     himo
    -0.63
    IndentedString
    -0.60
     esternos
    -0.59
    bootstrapcdn
    -0.59
     AssemblyCulture
    -0.56
    POSITIVE LOGITS
     evaluate
    0.44
     evaluar
    0.44
     might
    0.43
     considering
    0.43
     preguntas
    0.43
     appropriateness
    0.42
     whether
    0.42
     consideración
    0.40
     questions
    0.39
     considerar
    0.39
    Activations Density 0.002%

    No Known Activations