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. 667
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    56.25
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    questions and discussions regarding cause, effect, significance, and analysis in various contexts

    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
    ConstraintMaker
    -0.59
    EDEFAULT
    -0.58
     AssemblyCulture
    -0.57
     IFTT
    -0.54
    estacks
    -0.54
    doria
    -0.50
     Samaria
    -0.50
     immunos
    -0.50
    ]")]
    -0.50
    styleType
    -0.49
    POSITIVE LOGITS
     how
    0.47
     prospet
    0.39
     How
    0.38
     might
    0.38
     beyond
    0.37
     related
    0.37
     preguntas
    0.37
     questions
    0.36
     relacion
    0.36
     relacionado
    0.36
    Activations Density 0.040%

    No Known Activations