© 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 - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 406
    Prev
    Next
    INDEX
    Explanations

    references to programming concepts and data types

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

    code identifiers follow conclusions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     autorytatywna
    -0.76
    httphttps
    -0.66
     للاسماء
    -0.57
     الرياضيه
    -0.56
    ьаж
    -0.54
    脚注の使い方
    -0.52
     Italijanski
    -0.51
    principalTable
    -0.51
    RTLR
    -0.50
     kaynağından
    -0.48
    POSITIVE LOGITS
     therefore
    0.58
     hence
    0.53
    จึง
    0.52
     thus
    0.52
     portanto
    0.48
     therefor
    0.45
     accordingly
    0.45
     Infór
    0.44
    Hence
    0.42
     quindi
    0.42
    Activations Density 0.041%

    No Known Activations