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

    Neuronpedia

    APISteerSAE EvalsBlog/PodcastNEWSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 1
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    43.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    conditional statements and their associated syntax

    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
    AddTagHelper
    -0.51
    WriteTagHelper
    -0.46
     hendes
    -0.41
    reszcie
    -0.40
     AssemblyCulture
    -0.39
    Географиясе
    -0.36
    Diweddarwch
    -0.36
     himo
    -0.35
     panggilan
    -0.35
     legais
    -0.35
    POSITIVE LOGITS
     propOrder
    0.61
    Geplaatst
    0.50
    ResumeLayout
    0.50
    transQ
    0.47
    stdbool
    0.47
    optionalTypeArgs
    0.47
     ZDF
    0.45
    conditions
    0.45
     condi
    0.44
     if
    0.44
    Activations Density 0.225%

    No Known Activations