© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 41-GEMMASCOPE-RES-16K
    6. 6928
    Prev
    Next
    INDEX
    Explanations

    concepts related to mathematical structures and properties, particularly in category theory

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/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.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     CanadaChoose
    -0.40
    tonsoft
    -0.39
     Shoreline
    -0.35
    ItemBackground
    -0.35
    Географиясе
    -0.35
     pautas
    -0.35
    XmlAccessorType
    -0.34
     estate
    -0.34
    脚注の使い方
    -0.33
    
    -0.33
    POSITIVE LOGITS
     functor
    0.59
     homotopy
    0.52
     cohomology
    0.52
     Bous
    0.52
     comod
    0.51
     categories
    0.50
     Dwyer
    0.49
     homology
    0.49
     Kün
    0.47
     category
    0.46
    Activations Density 1.542%

    No Known Activations