© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 36-GEMMASCOPE-RES-16K
    11. 12125
    Prev
    Next
    INDEX
    Explanations

    elements related to conditional statements and dependencies in mathematical contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    !*\
    -0.39
    rungsseite
    -0.39
    værende
    -0.34
    
    -0.34
    おり
    -0.33
    uç
    -0.31
    Наводи
    -0.30
    isEnd
    -0.30
    しており
    -0.29
    ljiv
    -0.28
    POSITIVE LOGITS
     then
    4.63
     Then
    3.39
    then
    3.39
    Then
    3.38
     entonces
    3.25
     então
    3.06
     THEN
    3.06
     dann
    3.00
    THEN
    2.66
     тогда
    2.63
    Activations Density 4.018%

    No Known Activations