© 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. 38-GEMMASCOPE-RES-16K
    11. 12743
    Prev
    Next
    INDEX
    Explanations

    sentences with statistics or specific numerical references related to sports events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.65
    +#+#
    -0.62
    VersionUID
    -0.60
    QMetaType
    -0.57
    RectangleBorder
    -0.56
     تكبرها
    -0.52
    InstrumentedTest
    -0.51
    PyExc
    -0.51
     OMITBAD
    -0.50
     protoimpl
    -0.49
    POSITIVE LOGITS
     rookie
    0.48
     veteran
    0.46
     rookies
    0.45
     veterans
    0.40
     youngster
    0.38
     Josh
    0.36
     Jordan
    0.35
     vets
    0.35
     newcomer
    0.35
     blessé
    0.35
    Activations Density 0.187%

    No Known Activations