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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 5256
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    62.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    formal, technical language and structured references to data and parameters

    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
    WriteTagHelper
    -0.49
     Audiodateien
    -0.46
    ècie
    -0.46
    Personendaten
    -0.45
    Smarty
    -0.45
    DCHECK
    -0.45
    httphttps
    -0.43
    TAGE
    -0.40
     lizenzfreies
    -0.39
     Songtext
    -0.39
    POSITIVE LOGITS
    efois
    0.42
     arché
    0.42
    才會
    0.40
    NOPQRST
    0.40
    patrón
    0.39
    webElementXpaths
    0.39
     verrez
    0.38
     PyTuple
    0.38
     contextLoads
    0.38
     fréquence
    0.38
    Activations Density 0.008%

    No Known Activations