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. 154
    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

    complex emotional states and themes involving danger and uncertainty

    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
    tificates
    -0.50
    LabelTagHelper
    -0.49
     biodegradable
    -0.47
     bestemt
    -0.47
     święta
    -0.46
     Audiodateien
    -0.46
     AssemblyCulture
    -0.46
    ditionally
    -0.45
    indépendance
    -0.44
    akaian
    -0.44
    POSITIVE LOGITS
     encounters
    0.56
     encounter
    0.55
     risk
    0.54
     risky
    0.52
     perilous
    0.51
     dangers
    0.50
     danger
    0.50
     dangerous
    0.45
    risk
    0.45
     perils
    0.44
    Activations Density 0.009%

    No Known Activations