© 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. 14221
    Prev
    Next
    INDEX
    Explanations

    terms related to sports positions and statistics

    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
     sereia
    -0.43
     llorando
    -0.40
     goutte
    -0.39
     húmedo
    -0.38
     yeşil
    -0.38
     poussière
    -0.38
     linho
    -0.37
    colgante
    -0.37
     desnuda
    -0.37
    Salut
    -0.37
    POSITIVE LOGITS
     prowess
    0.62
    wpi
    0.55
     JScrollPane
    0.47
    /**
    0.47
     maven
    0.46
    formik
    0.46
    ftal
    0.46
     supremacy
    0.46
    Formik
    0.45
     exploits
    0.45
    Activations Density 0.379%

    No Known Activations