© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 5260
    Prev
    Next
    INDEX
    Explanations

    elements related to library linking and management in programming or software development 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
    doGet
    -0.36
     desplie
    -0.35
    anze
    -0.35
     desple
    -0.34
     plan
    -0.33
    __":
    -0.32
    ftagPool
    -0.31
    下载附件
    -0.31
    égio
    -0.31
     flow
    -0.31
    POSITIVE LOGITS
     DLL
    0.60
     EconPapers
    0.57
     CommonModule
    0.57
    DllImport
    0.56
     المعيارى
    0.55
    DLL
    0.55
    SpringBootTest
    0.55
    
    0.54
    dll
    0.52
     AssemblyVersion
    0.52
    Activations Density 0.505%

    No Known Activations