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. 1206
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    62
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    phrases indicating the need for verification or confirmation

    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
    tanleria
    -0.44
     TextAppearance
    -0.42
    WriteTagHelper
    -0.42
    lyrics
    -0.41
    pośred
    -0.40
     clearColor
    -0.40
     ​​
    -0.39
    deus
    -0.39
     metast
    -0.39
    Smarty
    -0.38
    POSITIVE LOGITS
    ValueStyle
    0.57
     kasarigan
    0.54
     verify
    0.53
     확인
    0.53
    efois
    0.51
    Chham
    0.50
     Véri
    0.50
    ########.
    0.49
     vérification
    0.46
     verification
    0.46
    Activations Density 0.267%

    No Known Activations