© 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. 14-GEMMASCOPE-RES-16K
    11. 11089
    Prev
    Next
    INDEX
    Explanations

    reserved keywords and classes in programming code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_14/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nearly
    -0.36
    iarkan
    -0.35
     Privacidad
    -0.35
     focused
    -0.32
    Географија
    -0.31
     esquecer
    -0.31
     inward
    -0.30
     Gegenwart
    -0.30
    ッタリ
    -0.29
     alugar
    -0.29
    POSITIVE LOGITS
    ⤹
    0.66
     Employee
    0.65
    WebServlet
    0.64
     Promotion
    0.56
     matric
    0.56
    Vidite
    0.55
    RegressionTest
    0.55
     Fac
    0.55
     Fingerprint
    0.54
     employee
    0.54
    Activations Density 0.065%

    No Known Activations