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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 28909
    Prev
    Next
    INDEX
    Explanations

    references to advantages or positive outcomes in various contexts

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

    advantages and positive outcomes

    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
    ništ
    -0.52
     geïsole
    -0.45
     Kaufman
    -0.45
    ajuku
    -0.44
     stuks
    -0.44
     lanterns
    -0.44
     Franke
    -0.43
    toThrow
    -0.43
     toalha
    -0.43
    setAddress
    -0.42
    POSITIVE LOGITS
     benefits
    1.17
     Benefits
    1.08
    Benefits
    1.05
    benefits
    1.05
     advantages
    0.97
    Benefit
    0.88
     avantages
    0.87
     BENEFITS
    0.85
     benefit
    0.85
    benefit
    0.85
    Activations Density 0.041%

    No Known Activations