© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 12634
    Prev
    Next
    INDEX
    Explanations

    specific numerical values and terms related to chess or competitive events

    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
    Билгалдахарш
    -0.57
    ftagPool
    -0.54
    WithIOException
    -0.49
    ectoria
    -0.49
     lenker
    -0.48
     Competi
    -0.47
     Expectations
    -0.46
    ranet
    -0.46
     Append
    -0.45
     carab
    -0.45
    POSITIVE LOGITS
     &___
    0.48
    setLayoutManager
    0.40
     posesión
    0.38
     שוליים
    0.36
     pintados
    0.34
    uidado
    0.32
    seamnă
    0.32
     cancelación
    0.31
     ganchillo
    0.30
     conmigo
    0.30
    Activations Density 0.124%

    No Known Activations