© 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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 104588
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts or formal documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
     UIKit
    -0.37
     máximo
    -0.34
    でございます
    -0.33
    Источники
    -0.32
    ※
    -0.32
    しております
    -0.30
    と思われます
    -0.30
    していく
    -0.29
     çalışan
    -0.29
     gjøre
    -0.29
    POSITIVE LOGITS
    AddHtmlAttribute
    0.79
    GOTREF
    0.73
     surla
    0.70
    principalColumn
    0.69
     Wikimedijinoj
    0.69
    iſchen
    0.65
    createServer
    0.64
    ScopeManager
    0.64
     مرئيه
    0.64
     informée
    0.63
    Activations Density 0.055%

    No Known Activations