© 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. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 54699
    Prev
    Next
    INDEX
    Explanations

    words and phrases that express preferences, confirmations, and evaluations in various languages

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

    good, better, best, bad, confirmation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.57
     unleash
    -0.46
    orghini
    -0.45
    assertRaises
    -0.45
     *)__
    -0.44
    lament
    -0.43
     Gallardo
    -0.43
    []):
    -0.43
     resourceCulture
    -0.43
    [])
    -0.43
    POSITIVE LOGITS
     tốt
    1.44
     baik
    1.31
    ดี
    1.21
     Baik
    1.01
    Baik
    0.97
     goed
    0.94
    good
    0.86
     good
    0.86
     terbaik
    0.86
     Good
    0.85
    Activations Density 0.002%

    No Known Activations