© 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. 24-GEMMASCOPE-RES-16K
    11. 10108
    Prev
    Next
    INDEX
    Explanations

    significant achievements or impactful moments in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Victory, winning, or clutch moments

    np_acts-logits-general · gemini-2.0-flash

    clutch late game winners

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     continúas
    -0.39
    Продол
    -0.34
    occuper
    -0.33
    couz
    -0.33
     tela
    -0.33
    ViewFeatures
    -0.32
    Marshaller
    -0.32
     camiset
    -0.31
     modelAndView
    -0.31
     onResume
    -0.30
    POSITIVE LOGITS
     clutch
    0.62
    Clutch
    0.60
     victory
    0.60
     Clutch
    0.57
     late
    0.56
    FINAL
    0.54
    Late
    0.54
     decisivo
    0.54
    final
    0.52
     thrilling
    0.52
    Activations Density 0.132%

    No Known Activations