© 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. 9408
    Prev
    Next
    INDEX
    Explanations

    constructs that indicate loops and iterations in programming logic

    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
    MLLoader
    -0.88
     ModelExpression
    -0.71
     насељу
    -0.68
    featureID
    -0.66
     arşivlendi
    -0.65
     autorytatywna
    -0.65
    ロウィン
    -0.64
    يكب
    -0.63
     MainAxisSize
    -0.63
    CloseOperation
    -0.62
    POSITIVE LOGITS
     j
    0.57
     counter
    0.56
     loop
    0.52
    loop
    0.46
    counter
    0.40
    j
    0.40
     k
    0.39
     loops
    0.38
    Counter
    0.37
    Loop
    0.36
    Activations Density 0.214%

    No Known Activations