© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 7443
    Prev
    Next
    INDEX
    Explanations

    phrases indicating speculation or contemplation about future events or outcomes

    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
    后来
    -0.57
    toplankton
    -0.56
     autorytatywna
    -0.56
    PerformLayout
    -0.54
    後來
    -0.53
     للمعارف
    -0.52
     pinulongan
    -0.50
     fometimes
    -0.50
     sometimes
    -0.50
    是因為
    -0.50
    POSITIVE LOGITS
     hopefully
    1.09
    Fingers
    1.08
     Hopefully
    1.06
    Hopefully
    1.03
     Fingers
    1.00
     fingers
    0.95
    hopefully
    0.94
    fingers
    0.94
    🤞
    0.92
    Assuming
    0.80
    Activations Density 0.408%

    No Known Activations