© 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 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. 13384
    Prev
    Next
    INDEX
    Explanations

    references to recycling programs or committees

    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
     🥰
    -1.15
     covid
    -1.10
     COVID
    -1.05
     pandemia
    -1.03
    COVID
    -0.98
     🤣
    -0.98
     Covid
    -0.97
    ️⃣
    -0.97
     https
    -0.97
    🥰
    -0.97
    POSITIVE LOGITS
     idéia
    1.05
    http
    0.66
     europé
    0.64
     Bewußt
    0.63
     http
    0.63
     mußten
    0.60
     Einfluß
    0.58
     xrange
    0.56
    myspace
    0.56
     Miß
    0.56
    Activations Density 1.085%

    No Known Activations