© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B-IT
    5. 20-AXBENCH-REFT-R1-RES-16K
    7. 4053
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    55.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    punctuation marks and formatting elements, as well as recognize numerical representations in the text

    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
    tagext
    -0.47
    localctx
    -0.42
    isième
    -0.40
    andExpect
    -0.35
    󠁣
    -0.35
    wood
    -0.35
    észetes
    -0.35
    pholes
    -0.35
    ůměr
    -0.35
     backlight
    -0.34
    POSITIVE LOGITS
    ########.
    0.51
    PullParser
    0.48
     Taktlose
    0.47
     kasarigan
    0.45
     MenuView
    0.45
     CreateTagHelper
    0.45
    AsUp
    0.44
    ruptedException
    0.43
    MigrationBuilder
    0.43
     '\\;'
    0.42
    Activations Density 1.961%

    No Known Activations