© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 0-GEMMASCOPE-RES-16K
    11. 12610
    Prev
    Next
    INDEX
    Explanations

    occurences of array-related terminology in programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    awtextra
    -0.79
    centralwidget
    -0.66
     Merry
    -0.64
     Shop
    -0.63
     fe
    -0.63
     ste
    -0.63
     Pag
    -0.62
     Vic
    -0.61
     Kem
    -0.61
    ibatis
    -0.60
    POSITIVE LOGITS
     Grecs
    0.50
    berdayakan
    0.46
    čenje
    0.44
     Keuangan
    0.43
     abundancia
    0.43
     življen
    0.43
     hjælp
    0.42
     almofada
    0.42
    Enum
    0.42
     hidratante
    0.41
    Activations Density 0.552%

    No Known Activations