© 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. 14275
    Prev
    Next
    INDEX
    Explanations

    terms that indicate visibility, clarity, and detail in descriptions

    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
    HandlerContext
    -0.40
    inSlope
    -0.37
    testng
    -0.36
    httphttps
    -0.35
    тельность
    -0.34
    Biographie
    -0.33
    Награды
    -0.33
     Klä
    -0.32
    Xna
    -0.31
    封装
    -0.31
    POSITIVE LOGITS
     visible
    3.08
     Visible
    2.66
    visible
    2.61
     visibles
    2.41
    Visible
    2.38
     visibility
    2.00
     zicht
    1.98
     sicht
    1.96
     noticeable
    1.95
     visibly
    1.88
    Activations Density 1.084%

    No Known Activations