© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 13464
    Prev
    Next
    INDEX
    Explanations

    references to specific national or political entities and their agreements or deals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.88
    writeFieldEnd
    -0.73
     OFDb
    -0.70
    RegressionTest
    -0.65
     disambiguazione
    -0.63
    GenerationType
    -0.58
    RTCF
    -0.58
    ArgsConstructor
    -0.57
    UnusedPrivate
    -0.56
     تعدى
    -0.56
    POSITIVE LOGITS
    DockStyle
    0.31
    potranspiration
    0.30
    UnsafeEnabled
    0.30
    ysaccharides
    0.29
    <bos>
    0.29
     Distrikt
    0.28
     bagay
    0.28
     erhöht
    0.28
     çek
    0.27
     INSPECTION
    0.27
    Activations Density 1.919%

    No Known Activations