© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 5884
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    60.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    words related to formal institutions and legal constructs

    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
     esternos
    -0.46
    SequentialGroup
    -0.42
    $_['
    -0.42
    tanleria
    -0.41
    sistors
    -0.40
    Smarty
    -0.38
    >')
    -0.37
     switch
    -0.37
     nawr
    -0.36
     referenties
    -0.36
    POSITIVE LOGITS
    ValueStyle
    0.51
     purpoſe
    0.50
     betweenstory
    0.45
     ainfi
    0.45
    ſelf
    0.45
     Normdatei
    0.43
    團體
    0.42
     délé
    0.41
     للمعارف
    0.41
    ftance
    0.41
    Activations Density 1.137%

    No Known Activations