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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 1204
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    78
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to healing during difficult situations

    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
     Paglinawan
    -0.58
    ikusbot
    -0.50
     modernize
    -0.50
     AssemblyCulture
    -0.49
     Audiodateien
    -0.48
     Larg
    -0.48
    arsk
    -0.44
     مرئيه
    -0.44
    andExpect
    -0.44
     automate
    -0.44
    POSITIVE LOGITS
    HandlerContext
    0.46
    fromnode
    0.41
    ValueStyle
    0.40
     JAXB
    0.40
     épreuves
    0.38
     apoyo
    0.38
    FormState
    0.38
     createContext
    0.38
    Trayectoria
    0.37
     relâche
    0.37
    Activations Density 0.000%

    No Known Activations