© 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. 6448
    Prev
    Next
    INDEX
    Explanations

    actions and descriptors related to physical movement and interactions

    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
     simplicité
    -0.36
    ngdoc
    -0.35
     accidentes
    -0.34
     kalangan
    -0.32
     çe
    -0.32
     perfección
    -0.31
     excelencia
    -0.31
     ángeles
    -0.31
    ANTAGES
    -0.30
    fiez
    -0.30
    POSITIVE LOGITS
     bags
    1.06
     suitcases
    1.02
     papers
    0.98
     bottles
    0.98
     luggage
    0.94
     towels
    0.94
     suitcase
    0.93
     cigarettes
    0.92
     notebooks
    0.92
     blankets
    0.90
    Activations Density 0.630%

    No Known Activations