© 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. 22-GEMMASCOPE-RES-16K
    11. 4495
    Prev
    Next
    INDEX
    Explanations

    instances of the keyword "new" and class declarations in the context of programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     náv
    -0.52
    URBANA
    -0.51
     sebab
    -0.47
     sebaliknya
    -0.47
     pokud
    -0.47
     acá
    -0.46
     avena
    -0.46
    gsmål
    -0.45
     jinak
    -0.45
     afuera
    -0.45
    POSITIVE LOGITS
     new
    0.86
     New
    0.69
     تضيفلها
    0.64
    new
    0.62
     small
    0.56
     NEW
    0.56
     tiny
    0.55
     huge
    0.55
     a
    0.55
     few
    0.54
    Activations Density 0.064%

    No Known Activations