© 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. 600
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    72
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    concepts related to social justice and equity issues

    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
    -0.67
    WriteTagHelper
    -0.63
    andExpect
    -0.59
    GEBURTSDATUM
    -0.57
    zheimer
    -0.57
    estacks
    -0.56
     AssemblyCulture
    -0.56
    AsNil
    -0.54
    :✨
    -0.54
     Audiodateien
    -0.54
    POSITIVE LOGITS
     égale
    0.40
     betweenstory
    0.35
     discriminación
    0.35
     valorar
    0.35
     muestra
    0.35
     igualdad
    0.35
     temáticas
    0.35
    gjenge
    0.34
     mujeres
    0.34
     oportunidades
    0.33
    Activations Density 0.004%

    No Known Activations