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

    Neuronpedia

    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. 31-GEMMASCOPE-RES-16K
    11. 6249
    Prev
    Next
    INDEX
    Explanations

    Japanese characters or terms related to language nuances

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

    This neuron appears to be activating on random fragments across diverse, unrelated documents (technical documentation, religious texts, genealogy, historical records) without a clear semantic pattern, suggesting it may be detecting spurious statistical artifacts or encoding noise rather than any meaningful linguistic feature.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/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.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.60
     EconPapers
    -0.57
    ="@+
    -0.57
     ujednoznacz
    -0.48
     intStringLen
    -0.48
    awtextra
    -0.45
    XmlEnum
    -0.44
    UnusedPrivate
    -0.42
     ModelExpression
    -0.41
    MigrationBuilder
    -0.41
    POSITIVE LOGITS
    mas
    0.54
     mas
    0.45
    lamine
    0.44
     gustó
    0.44
    mens
    0.43
    ammer
    0.43
    tase
    0.43
    ggi
    0.43
    master
    0.43
    Mas
    0.41
    Activations Density 0.037%

    No Known Activations