© 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. 14167
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax or functions

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

    underscores and parentheses in code and markup syntax.

    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
     surla
    -0.78
     ujednoznacz
    -0.75
     betweenstory
    -0.73
     noDo
    -0.73
     EconPapers
    -0.72
    httphttps
    -0.71
    tagext
    -0.67
     &___
    -0.66
     initComponents
    -0.65
    iocene
    -0.65
    POSITIVE LOGITS
     nødven
    0.43
     arbejds
    0.40
     наоборот
    0.38
     læng
    0.37
     dezelve
    0.36
     reducido
    0.36
     Vordergrund
    0.36
     nødvendig
    0.35
     görüntüsü
    0.35
    est
    0.35
    Activations Density 1.677%

    No Known Activations