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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 233
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    69.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to food, cooking, and culinary experiences

    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
    Personendaten
    -0.53
     Audiodateien
    -0.53
    /*++
    -0.48
    asteroide
    -0.47
    Parcelize
    -0.47
     Ανακτήθηκε
    -0.46
    agoza
    -0.46
    httphttps
    -0.46
    LabelTagHelper
    -0.46
     elettrica
    -0.45
    POSITIVE LOGITS
     للمعارف
    0.49
     culinary
    0.48
    TypedDataSet
    0.45
     cuisine
    0.42
    fromnode
    0.42
     food
    0.41
     cooking
    0.41
    food
    0.38
     tasty
    0.38
    Cooking
    0.38
    Activations Density 0.001%

    No Known Activations