© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 79873
    Prev
    Next
    INDEX
    Explanations

    instances of the word "good" and its variations, indicating an emphasis on positivity and quality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     consider
    -0.42
     opt
    -0.39
    nungen
    -0.38
     threat
    -0.38
    DataSnapshot
    -0.38
     for
    -0.37
    rawQuery
    -0.36
     הרי
    -0.36
     appeal
    -0.36
     compel
    -0.35
    POSITIVE LOGITS
    OGND
    0.64
    quality
    0.61
     quality
    0.60
     дописавши
    0.58
    Quality
    0.57
     kwaliteit
    0.56
     ویکی‌پدیا
    0.56
     QUALITY
    0.56
     Quality
    0.56
     للاسماء
    0.56
    Activations Density 0.020%

    No Known Activations