© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 2646
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with logic and programming concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     koji
    -0.67
     său
    -0.65
     himself
    -0.62
    Completo
    -0.55
     américain
    -0.54
     féminin
    -0.53
     који
    -0.52
     urbano
    -0.50
     męski
    -0.48
     Jr
    -0.48
    POSITIVE LOGITS
     herself
    0.92
    herself
    0.80
     koja
    0.68
     która
    0.66
     která
    0.65
     которую
    0.63
     ktorá
    0.63
     которая
    0.62
     која
    0.61
     कैसी
    0.57
    Activations Density 0.122%

    No Known Activations