© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 6193
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    quotations and punctuations that indicate dialogue or speech

    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
    OrBuilder
    -0.35
     
    -0.32
    isième
    -0.30
     adulta
    -0.30
     angelegt
    -0.30
    wood
    -0.29
     aside
    -0.29
    endente
    -0.28
    DCHECK
    -0.28
     powder
    -0.28
    POSITIVE LOGITS
    ſelf
    0.68
     '\\;'
    0.65
    ########.
    0.63
     propOrder
    0.62
     raiſ
    0.61
     purpoſe
    0.60
     ſta
    0.59
    InstrumentedTest
    0.59
     kasarigan
    0.58
     noDo
    0.58
    Activations Density 2.099%

    No Known Activations