© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 8824
    Prev
    Next
    INDEX
    Explanations

    terms related to invention and discovery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Roumanie
    -0.65
    BagConstraints
    -0.63
    mobileqq
    -0.62
    
    -0.59
     pewno
    -0.59
    CodeAnalysis
    -0.58
    verwijspagina
    -0.58
     ortodo
    -0.56
    udsman
    -0.55
     rispet
    -0.54
    POSITIVE LOGITS
     invent
    1.38
     Invent
    1.26
     discovery
    1.23
     invention
    1.13
     inventing
    1.08
     invented
    1.07
     inventor
    1.02
    invent
    1.01
     Invention
    1.00
     inven
    0.98
    Activations Density 0.082%

    No Known Activations