© 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. 20-GEMMASCOPE-RES-16K
    6. 7685
    Prev
    Next
    INDEX
    Explanations

    code structures and syntax related to function definitions in programming languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     deği
    -0.56
     فريبيس
    -0.54
    dafx
    -0.49
     Durchmesser
    -0.47
     tamaños
    -0.47
    圖片來源
    -0.45
     tallas
    -0.45
     ileti
    -0.44
    GeoNames
    -0.44
     gramos
    -0.43
    POSITIVE LOGITS
    MemoryWarning
    0.55
    IBOutlet
    0.53
     Taktlose
    0.49
     nonUne
    0.49
    IUrlHelper
    0.49
     ComVisible
    0.45
    awtextra
    0.43
    bry
    0.43
        
    0.42
    override
    0.42
    Activations Density 0.209%

    No Known Activations