© 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. 11-GEMMASCOPE-RES-16K
    11. 6671
    Prev
    Next
    INDEX
    Explanations

    technical terms and codes related to healthcare or medical studies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     engraçadas
    -0.54
     picioare
    -0.52
    RegressionTest
    -0.49
    Referanser
    -0.48
    Erstellt
    -0.45
    ValueStyle
    -0.45
     munc
    -0.44
     alcuna
    -0.44
    XmlAccessType
    -0.43
    󠁢
    -0.43
    POSITIVE LOGITS
    UnusedPrivate
    0.51
     AssemblyCulture
    0.50
    IndentedString
    0.49
    thâu
    0.48
    TintMode
    0.43
     noDo
    0.41
    parsedMessage
    0.40
    Datuak
    0.40
    MeasureSpec
    0.40
     تكبرها
    0.40
    Activations Density 10.808%

    No Known Activations