© 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
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 10137
    Prev
    Next
    INDEX
    Explanations

    references to specific game elements and features related to various gaming genres and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rüyada
    -0.36
     tempio
    -0.36
     aikana
    -0.35
     kalite
    -0.34
    Swimming
    -0.34
     frattempo
    -0.32
    styleType
    -0.32
     écrits
    -0.32
     cejas
    -0.31
    malı
    -0.30
    POSITIVE LOGITS
    脚注の使い方
    0.70
    AnchorStyles
    0.61
    oredCriteria
    0.59
    Билгалдахарш
    0.59
    ScopeManager
    0.54
    Искәрмәләр
    0.53
    PageContext
    0.53
    expandindo
    0.52
    ніципа
    0.52
    WebServlet
    0.52
    Activations Density 0.486%

    No Known Activations