© 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. 15-GEMMASCOPE-RES-16K
    11. 2707
    Prev
    Next
    INDEX
    Explanations

    references to theorems and lemmas within mathematical texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    idane
    -0.45
    gypti
    -0.45
    Quiénes
    -0.43
     alimentare
    -0.42
    jets
    -0.42
    jet
    -0.42
    ymce
    -0.42
    越
    -0.42
    (['/
    -0.41
    Externé
    -0.41
    POSITIVE LOGITS
    Theorem
    0.98
     Theorem
    0.88
     theorem
    0.84
    THEOREM
    0.81
    Corollary
    0.79
     theorems
    0.73
    theorem
    0.72
     AssemblyCulture
    0.69
     Theorems
    0.67
    Lemma
    0.66
    Activations Density 0.897%

    No Known Activations