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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 5556
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    73.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    various types of hospitals and medical centers

    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
    Personendaten
    -0.66
     OFDb
    -0.55
    Diweddarwch
    -0.55
    GEBURTSDATUM
    -0.55
    pexpr
    -0.52
     OMITBAD
    -0.49
    Kariera
    -0.47
    bVar
    -0.47
    OGND
    -0.46
    MenuInflater
    -0.46
    POSITIVE LOGITS
     hospitals
    0.52
     institutions
    0.47
     universities
    0.45
     hospital
    0.44
     éduc
    0.41
     University
    0.40
     Hospital
    0.40
     instituição
    0.40
    Hospitals
    0.39
    University
    0.39
    Activations Density 0.012%

    No Known Activations