© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 13010
    Prev
    Next
    INDEX
    Explanations

    LaTeX commands or syntax elements often used in mathematical or scientific documents

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

    mathematics

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     ब्रेकडाउन
    -1.09
    Personendaten
    -0.96
     autorytatywna
    -0.94
     témoig
    -0.73
    ロウィン
    -0.73
    WriteBarrier
    -0.70
     increí
    -0.70
     パンチラ
    -0.69
    <pad>
    -0.68
    <unused3>
    -0.68
    POSITIVE LOGITS
     math
    0.61
     Mathematics
    0.58
     Math
    0.57
     mathematics
    0.54
     mathematical
    0.48
    math
    0.48
     Mathematical
    0.47
    Math
    0.47
     Department
    0.45
     MATH
    0.43
    Activations Density 0.004%

    No Known Activations