© 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. 15-GEMMASCOPE-RES-16K
    11. 5192
    Prev
    Next
    INDEX
    Explanations

    mathematical or scientific notation and symbols

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarvit
    -0.28
    PONENTS
    -0.28
     Schreiber
    -0.27
     Orozco
    -0.26
    тифика
    -0.25
     hóspedes
    -0.25
    mesine
    -0.25
     apariencia
    -0.25
     contrats
    -0.25
    Pranala
    -0.24
    POSITIVE LOGITS
     nahilalakip
    0.69
    ItemBackground
    0.65
    MLLoader
    0.64
     AssemblyCompany
    0.63
    featureID
    0.60
     ModelExpression
    0.59
     CURIAM
    0.59
    Vidite
    0.59
     للاسماء
    0.59
     Italijanski
    0.58
    Activations Density 2.230%

    No Known Activations