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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45710
    Prev
    Next
    INDEX
    Explanations

    variations of the word "OK" indicating approval or acceptance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    ok

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     TMS
    -0.42
     experience
    -0.42
    firestore
    -0.41
    matrix
    -0.40
     turi
    -0.40
     the
    -0.39
    ante
    -0.39
    ysty
    -0.38
     The
    -0.37
     transform
    -0.37
    POSITIVE LOGITS
    Ok
    1.02
     Ok
    0.98
     OK
    0.97
     ok
    0.93
    ok
    0.88
    OK
    0.88
    isOk
    0.85
     Okada
    0.81
    addGap
    0.73
    OkHttpClient
    0.71
    Activations Density 0.007%

    No Known Activations