© 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. 15-GEMMASCOPE-RES-16K
    11. 1191
    Prev
    Next
    INDEX
    Explanations

    references to waking up and mornings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     further
    -0.40
     elements
    -0.37
    Elements
    -0.35
     offer
    -0.32
     Elements
    -0.31
     pieces
    -0.31
    elements
    -0.29
     Borden
    -0.29
     future
    -0.29
     Further
    -0.29
    POSITIVE LOGITS
     woken
    1.05
    Wake
    1.04
     waking
    0.99
    wake
    0.98
     wakes
    0.95
     Wake
    0.94
     wake
    0.93
    awake
    0.91
     awake
    0.90
    WAKE
    0.89
    Activations Density 0.201%

    No Known Activations