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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 863
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    55
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and emphatic expressions

    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
    wayat
    -0.35
     recognised
    -0.33
    wood
    -0.33
    mans
    -0.33
     Wylie
    -0.32
     SqlDbType
    -0.32
     Freire
    -0.32
    farwyddwr
    -0.31
     Tuchel
    -0.31
    Litteratur
    -0.30
    POSITIVE LOGITS
    
    0.72
     noDo
    0.63
     насељу
    0.63
    transQ
    0.61
    webElementXpaths
    0.61
    InstrumentedTest
    0.61
     queſta
    0.61
    +#+#
    0.60
    fromnode
    0.60
    majánló
    0.58
    Activations Density 1.697%

    No Known Activations