© 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. 1-GEMMASCOPE-RES-16K
    11. 8011
    Prev
    Next
    INDEX
    Explanations

    words related to ordering processes and customer transactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.72
    enderror
    -0.66
    HomeAsUpEnabled
    -0.66
    IntoConstraints
    -0.66
    DockStyle
    -0.64
    numerusform
    -0.63
    RRect
    -0.61
    InputTagHelper
    -0.61
     sogget
    -0.61
    RectangleBorder
    -0.60
    POSITIVE LOGITS
     ordering
    0.81
     ordered
    0.71
     Ordering
    0.69
     Ordered
    0.61
    ordering
    0.61
    <bos>
    0.55
     Lower
    0.54
     ORDERED
    0.50
    Ordered
    0.49
    ordered
    0.48
    Activations Density 0.401%

    No Known Activations