© 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. 10843
    Prev
    Next
    INDEX
    Explanations

    references to programming and data structures

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

    mathematical and scientific notation with subscripts and superscripts.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    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
    Autoritní
    -0.93
     fashiola
    -0.93
    StoryboardSegue
    -0.91
     tartalo
    -0.88
     erſten
    -0.88
     Menſchen
    -0.88
     ſeyn
    -0.87
    
    -0.87
    ㄰
    -0.87
    bildtitel
    -0.87
    POSITIVE LOGITS
    <bos>
    0.29
    _
    0.27
     intermédiaire
    0.27
     
    0.27
     počet
    0.26
     második
    0.25
     productividad
    0.25
    ...
    0.24
     ň
    0.24
     parete
    0.24
    Activations Density 0.701%

    No Known Activations