© 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. 36-GEMMASCOPE-RES-16K
    11. 8188
    Prev
    Next
    INDEX
    Explanations

    programming syntax and structure, particularly related to functions and returns

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.73
    DockStyle
    -0.65
    UnusedPrivate
    -0.64
    XmlAccessType
    -0.60
    LookAnd
    -0.52
     GenerationType
    -0.51
    AntiForgeryToken
    -0.51
     QName
    -0.50
    typeparam
    -0.49
    complexContent
    -0.49
    POSITIVE LOGITS
    berdayakan
    0.47
    ={`/
    0.39
    Читати
    0.34
    ívar
    0.34
     surla
    0.31
    
    0.31
    håll
    0.31
    pisah
    0.31
    ValueStyle
    0.31
    MENAFN
    0.31
    Activations Density 0.492%

    No Known Activations