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. 933
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    69.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    references to tables in a document

    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
    HttpFoundation
    -0.40
    DCHECK
    -0.38
     meisten
    -0.38
     offizi
    -0.36
     grossen
    -0.35
    -------------</
    -0.35
     offiziellen
    -0.35
     outlawed
    -0.35
     herrs
    -0.34
     παν
    -0.34
    POSITIVE LOGITS
    #+#
    0.60
    Chham
    0.58
    TypedDataSet
    0.58
    +#+#
    0.53
    ########.
    0.51
     autorytatywna
    0.49
     structured
    0.48
     snippetHide
    0.48
     tabular
    0.48
     rows
    0.48
    Activations Density 0.001%

    No Known Activations