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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 92849
    Prev
    Next
    INDEX
    Explanations

    elements related to web development concepts, specifically actions and controllers in programming frameworks

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

    action methods or controller endpoints

    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
     digitais
    -0.39
     jurado
    -0.39
    essentiel
    -0.35
     menghabiskan
    -0.35
     corrupción
    -0.35
     delegación
    -0.34
     logique
    -0.34
     nikt
    -0.34
     Ausrüstung
    -0.34
     sabiduría
    -0.33
    POSITIVE LOGITS
    ToAction
    0.84
     NavController
    0.81
    adaptiveStyles
    0.79
    extAlignment
    0.77
     ActionResult
    0.75
    UIControlState
    0.69
     مرئيه
    0.62
    
    0.60
     IActionResult
    0.60
    Tembelea
    0.60
    Activations Density 0.002%

    No Known Activations