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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-9B-IT
    3. 20-AXBENCH-REFT-R1-RES-16K
    4. 21
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    70.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    terms related to research methodologies and scientific validation

    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
    WriteTagHelper
    -0.55
    $_['
    -0.54
     SYLLABLE
    -0.54
    Smarty
    -0.51
     AssemblyCulture
    -0.48
    newArrayList
    -0.45
     Audiodateien
    -0.44
    лтемелер
    -0.43
    redient
    -0.42
    DCHECK
    -0.41
    POSITIVE LOGITS
     methodology
    0.58
     methodologies
    0.50
     betweenstory
    0.50
     research
    0.47
    ValueStyle
    0.46
     analysis
    0.45
     approach
    0.45
     CreateTagHelper
    0.45
     plan
    0.44
     procedures
    0.44
    Activations Density 0.001%

    No Known Activations