© 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. 36-GEMMASCOPE-RES-16K
    11. 7246
    Prev
    Next
    INDEX
    Explanations

    structured data references, particularly related to coding and API requests

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    V
    -1.24
    v
    -1.10
     V
    -1.08
     v
    -0.91
    VC
    -0.88
    vc
    -0.83
    VD
    -0.82
    Ｖ
    -0.79
    VP
    -0.79
    vd
    -0.77
    POSITIVE LOGITS
    RenderAtEndOf
    0.73
    httphttps
    0.69
     propOrder
    0.67
    -------------</
    0.66
    RTEE
    0.66
    出版年
    0.62
    Personendaten
    0.61
    ImageContext
    0.60
     MainAxisSize
    0.59
     initComponents
    0.59
    Activations Density 1.908%

    No Known Activations