© 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
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2522
    Prev
    Next
    INDEX
    Explanations

    variables and data structures frequently used in coding or programming contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     democrats
    -0.61
    dam
    -0.57
     dal
    -0.55
    danny
    -0.54
    darwin
    -0.54
    dang
    -0.54
    rungsseite
    -0.53
    dal
    -0.52
    dar
    -0.51
    deco
    -0.51
    POSITIVE LOGITS
     Đ
    0.82
     Ди
    0.80
     Di
    0.80
     Да
    0.74
     Da
    0.73
     Dé
    0.73
     Де
    0.70
     Д
    0.69
    Ди
    0.68
     Dt
    0.67
    Activations Density 1.186%

    No Known Activations