© 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-IT
    7. Residual Stream - 131k
    9. 31-GEMMASCOPE-RES-131K
    11. 5684
    Prev
    Next
    INDEX
    Explanations

    variable and function declarations in code snippets

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

    looping and counting variables

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     loginUser
    -0.43
     архивлан
    -0.42
     isShow
    -0.39
     eventName
    -0.38
     defStyleAttr
    -0.38
    niająca
    -0.37
     &[
    -0.37
     deleteById
    -0.36
    الدراسه
    -0.36
    postsleuth
    -0.36
    POSITIVE LOGITS
     counter
    0.73
     i
    0.67
     COUNTER
    0.59
     iterate
    0.57
     loop
    0.57
    counter
    0.56
     Counter
    0.56
     Iterate
    0.55
    foreach
    0.53
    Counter
    0.52
    Activations Density 0.010%

    No Known Activations