© 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. 509
    Prev
    Next
    INDEX
    Model
    gemma-2-9b-it
    Layer #
    20
    Steering Hook
    blocks.20.hook_resid_pre
    Steering Strength
    57.5
    Uploader
    bot-neuronpedia
    Created At
    2/15/2025 1:06:43 AM
    Raw Vector
    Actions
    Explanations

    expressions that define or assign values in mathematical or programming contexts

    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
     ब्रेकडाउन
    -0.59
    UpInside
    -0.50
     OMITBAD
    -0.42
     المعيارى
    -0.41
    omitempty
    -0.41
     OFDb
    -0.40
    WriteTagHelper
    -0.40
    OrNil
    -0.40
    OOTDTY
    -0.39
    pidou
    -0.39
    POSITIVE LOGITS
    LookAnd
    0.50
    esModule
    0.50
     PropertyChanged
    0.48
    AntiForgeryToken
    0.46
    InstrumentedTest
    0.45
     ISNI
    0.42
    peq
    0.42
    XmlAccessorType
    0.41
     kasarigan
    0.41
    fromnode
    0.41
    Activations Density 0.024%

    No Known Activations