© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 131k
    9. 24-GEMMASCOPE-RES-131K
    11. 1392
    Prev
    Next
    INDEX
    Explanations

    code and programming constructs, particularly related to array manipulation and sorting functions

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    sorting lists and sequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_131k/average_l0_97
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
     disambiguazione
    -0.65
    RenderAtEndOf
    -0.60
     nahilalakip
    -0.56
    发表于
    -0.55
    EDEFAULT
    -0.54
     المعيارى
    -0.52
     arşivlendi
    -0.49
     Numerade
    -0.47
    vician
    -0.47
     يتيمه
    -0.47
    POSITIVE LOGITS
     sorted
    0.66
    排序
    0.65
    sorted
    0.64
     sorting
    0.63
    SORT
    0.56
    sort
    0.56
     ordenar
    0.55
     Sorting
    0.54
     Sort
    0.52
    OrderBy
    0.52
    Activations Density 0.083%

    No Known Activations