© 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-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 867
    Prev
    Next
    INDEX
    Explanations

    phrases that quantify data or make statistical comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    àng
    -0.49
    eaus
    -0.48
    CardHeader
    -0.47
    acı
    -0.47
     edema
    -0.47
     harm
    -0.46
     عق
    -0.46
     VX
    -0.45
    aisons
    -0.45
     heterogeneity
    -0.45
    POSITIVE LOGITS
     AssemblyTitle
    0.87
    MLLoader
    0.81
    BindingResult
    0.76
    */].
    0.75
    WebServlet
    0.74
    AddTagHelper
    0.73
    /*
    0.72
     الدولى
    0.70
    MessageOf
    0.70
     numberOfRows
    0.68
    Activations Density 0.249%

    No Known Activations