© 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. 22-GEMMASCOPE-RES-16K
    11. 3567
    Prev
    Next
    INDEX
    Explanations

    phrases that convey assessment of quality and value in dining or service experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utafitiHapana
    -0.80
    󠁣
    -0.75
     يتيمه
    -0.74
    ConstraintMaker
    -0.73
    linawan
    -0.70
    ſicht
    -0.69
    niſſe
    -0.69
    تقاوى
    -0.68
    ésultats
    -0.68
     geſch
    -0.68
    POSITIVE LOGITS
     and
    0.27
     throughout
    0.27
     cohé
    0.24
     tallas
    0.24
    while
    0.23
     indifer
    0.22
     обслуживания
    0.22
    throughout
    0.22
     excepción
    0.21
     satisfecho
    0.21
    Activations Density 0.102%

    No Known Activations