© 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. 7590
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements and constructs in programming code or text

    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
    !*\
    -0.38
    rungsseite
    -0.38
    værende
    -0.36
    おり
    -0.34
    uç
    -0.32
    Наводи
    -0.30
    
    -0.30
    djangoproject
    -0.29
    isEnd
    -0.28
    coration
    -0.28
    POSITIVE LOGITS
     then
    4.72
    then
    3.48
     Then
    3.45
    Then
    3.45
     entonces
    3.33
     então
    3.13
     THEN
    3.13
     dann
    3.06
    THEN
    2.72
     тогда
    2.70
    Activations Density 4.780%

    No Known Activations