© 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. 40-GEMMASCOPE-RES-16K
    11. 4263
    Prev
    Next
    INDEX
    Explanations

    programming keywords and data types in a structured format

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imagui
    -1.90
    
    -1.88
     ſuo
    -1.86
    ᔡ
    -1.84
     unſer
    -1.83
     zwiſchen
    -1.82
     beſti
    -1.82
     erſten
    -1.82
     verſch
    -1.82
     deſſen
    -1.82
    POSITIVE LOGITS
     Relaciones
    0.06
     locura
    0.05
     Opiniones
    0.03
     emoción
    0.02
     venganza
    0.02
     istrinya
    0.01
     amistad
    0.00
     TRABAJO
    -0.00
     perdón
    -0.01
     profesión
    -0.01
    Activations Density 0.185%

    No Known Activations