© 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. 31-GEMMASCOPE-RES-16K
    6. 1469
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and formal representations in economic decision-making contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mathematical notation and equations in academic text.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    انجليز
    -0.36
     Compro
    -0.34
    ViewImports
    -0.33
     Normdatei
    -0.33
     fratern
    -0.32
     InputDecoration
    -0.31
    IGraphics
    -0.31
    ährend
    -0.30
     organik
    -0.30
     Sarmiento
    -0.30
    POSITIVE LOGITS
     utility
    0.70
     preferences
    0.63
     informée
    0.60
     préférences
    0.60
    utility
    0.60
    preferences
    0.58
     Utility
    0.57
     preferencias
    0.57
     preference
    0.56
     EconPapers
    0.56
    Activations Density 1.114%

    No Known Activations