© 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. 10095
    Prev
    Next
    INDEX
    Explanations

    statements about mathematical results and theorems, particularly those involving proofs and assumptions

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

    mathematical and academic document structure elements like theorems, propositions, definitions, and formal statement markers.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    references to theorems, propositions, and other numbered mathematical results in academic papers.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    formal result declarations and their introductions/references in mathematical papers (e.g., statements identifying and presenting main results within sections).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    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
    PerformLayout
    -0.55
    ſelf
    -0.54
    -------
    -0.53
    uxxxx
    -0.53
     houſe
    -0.52
    лтемелер
    -0.50
     怎样
    -0.50
    QMetaType
    -0.49
    EndProject
    -0.49
     kasarigan
    -0.48
    POSITIVE LOGITS
     theorem
    0.88
     Theorem
    0.81
    Theorem
    0.73
     proof
    0.68
     theorems
    0.67
     lemma
    0.67
     Lemma
    0.66
    Lemma
    0.65
     lemmas
    0.62
     THEOREM
    0.57
    Activations Density 1.513%

    No Known Activations