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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 45
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    50.75
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    specialized punctuation or formatting within text

    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
     /\.
    -0.36
    ),),
    -0.35
     onData
    -0.34
    Personendaten
    -0.34
    >//
    -0.33
     fach
    -0.32
    tagext
    -0.32
    -------------</
    -0.31
     WARRANTY
    -0.31
    ]>
    -0.30
    POSITIVE LOGITS
    bibfield
    0.71
     purpoſe
    0.64
    majánló
    0.60
     anſ
    0.59
    
    0.58
     myſelf
    0.57
     ſtand
    0.55
    ſicht
    0.55
     kasarigan
    0.54
     fubject
    0.54
    Activations Density 1.546%

    No Known Activations