© 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. 36-GEMMASCOPE-RES-16K
    11. 14660
    Prev
    Next
    INDEX
    Explanations

    phrases that describe foundational concepts or principles in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    expandindo
    -0.66
     wikipagina
    -0.59
    !*\
    -0.57
     externi
    -0.54
     برانيه
    -0.54
     للاسماء
    -0.53
    sizeCache
    -0.50
    testens
    -0.50
    MessageOf
    -0.49
    adaptiveStyles
    -0.48
    POSITIVE LOGITS
     foundation
    2.47
     foundations
    2.27
    foundation
    2.00
     basis
    1.97
     FOUNDATION
    1.75
     foundational
    1.70
    Foundation
    1.66
     Foundation
    1.63
    基础
    1.62
    basis
    1.62
    Activations Density 0.846%

    No Known Activations