© 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. 28-GEMMASCOPE-RES-16K
    11. 7323
    Prev
    Next
    INDEX
    Explanations

    programming keywords and structures, especially related to functions and control flow

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

    Code containing "while" loops

    np_acts-logits-general · gemini-2.0-flash

    while loops

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ffions
    -0.54
    sidemargin
    -0.51
     gabbana
    -0.50
     يتيمه
    -0.50
    rrggbb
    -0.47
    afficheront
    -0.47
    цездатний
    -0.47
     ſta
    -0.47
    polation
    -0.46
     ſte
    -0.46
    POSITIVE LOGITS
     while
    1.86
    while
    1.77
     mientras
    1.42
     WHILE
    1.42
     mentre
    1.40
     While
    1.39
     whilst
    1.38
     enquanto
    1.37
    While
    1.34
    WHILE
    1.20
    Activations Density 0.202%

    No Known Activations