© 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. 38-GEMMASCOPE-RES-16K
    11. 9664
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations, particularly those related to functions and equations in advanced mathematics and statistics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     referenties
    -0.35
    setLayoutParams
    -0.35
     Gid
    -0.34
    теристи
    -0.33
    secretary
    -0.33
     aten
    -0.33
     aid
    -0.33
    $<$
    -0.32
    MathML
    -0.32
     Sul
    -0.32
    POSITIVE LOGITS
    Personendaten
    0.70
     autorytatywna
    0.61
    +#+
    0.56
    
    0.55
    +#+#
    0.51
     disambiguazione
    0.51
    +\
    0.50
    Tembelea
    0.48
    StoryboardSegue
    0.48
    InsertCommand
    0.45
    Activations Density 2.212%

    No Known Activations