© 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. 35-GEMMASCOPE-RES-16K
    11. 14002
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific references to names, places, and products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    sizeCache
    -0.97
    enterOuterAlt
    -0.90
    DockStyle
    -0.85
     оригіналу
    -0.75
    tangentMode
    -0.75
     Numerade
    -0.75
    vician
    -0.74
    -------------</
    -0.72
    #+#
    -0.71
    httphttps
    -0.70
    POSITIVE LOGITS
     etc
    1.05
     semuanya
    0.97
     allemaal
    0.94
     등
    0.89
     among
    0.88
    などなど
    0.88
    等等
    0.87
    etc
    0.85
     respectively
    0.85
     serta
    0.82
    Activations Density 1.021%

    No Known Activations