© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 21597
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ributions
    -0.60
     Xunit
    -0.58
    arn
    -0.42
    SpringBootTest
    -0.41
     summary
    -0.39
     oral
    -0.38
    ModelState
    -0.38
     باد
    -0.38
    horiz
    -0.37
    <eos>
    -0.37
    POSITIVE LOGITS
    Décès
    5.69
    Naissance
    1.16
     surla
    0.91
     للمعارف
    0.90
    Personendaten
    0.90
    Aiheesta
    0.81
    GEBURTSDATUM
    0.80
     يتيمه
    0.79
     незавершена
    0.78
    يميديا
    0.77
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.