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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 47527
    Prev
    Next
    INDEX
    Explanations

    references to low-cost travel and budget-related topics

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

    airlines, airports, and outlets

    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
     Infórmanos
    -0.64
    Abit
    -0.55
    writeFieldEnd
    -0.53
    Personendaten
    -0.53
     فريبيس
    -0.52
    gamesh
    -0.50
    
    -0.49
    exao
    -0.49
    Біографія
    -0.49
    webElementXpaths
    -0.48
    POSITIVE LOGITS
    anair
    0.69
     Ryanair
    0.47
    PreferredItem
    0.43
     EconPapers
    0.41
     cheap
    0.37
    ArrowToggle
    0.37
     Anarchy
    0.35
    ppchen
    0.34
     UIKit
    0.34
     Lidl
    0.33
    Activations Density 0.005%

    No Known Activations