© 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. 8460
    Prev
    Next
    INDEX
    Explanations

    code-related constructs and syntactical elements in programming or markup languages

    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
    extAlignment
    -0.42
    
    -0.38
     skimage
    -0.36
     BitmapFactory
    -0.36
     surla
    -0.33
    setViewportView
    -0.33
    Gemeinden
    -0.31
     okhttp
    -0.30
    TextInputLayout
    -0.30
    wpi
    -0.30
    POSITIVE LOGITS
     nonUne
    0.85
     EconPapers
    0.77
     NSCoder
    0.74
    ValueStyle
    0.73
     Autorizaciones
    0.73
    CppMethod
    0.69
    ंदीखरीदारी
    0.69
     noDo
    0.69
     TestBed
    0.67
    KommentareTeilen
    0.66
    Activations Density 2.586%

    No Known Activations