© 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. 14381
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods, exclamation points, and question marks in the text

    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
     linebacker
    -0.47
     them
    -0.46
     motocross
    -0.46
     airlines
    -0.45
     manslaughter
    -0.45
     rodeo
    -0.44
     sedan
    -0.44
     goalie
    -0.43
     him
    -0.43
     banderas
    -0.43
    POSITIVE LOGITS
     They
    1.10
     The
    1.09
     This
    1.06
     It
    1.04
     Also
    0.95
     That
    0.94
     There
    0.94
     In
    0.88
     And
    0.88
     Their
    0.88
    Activations Density 2.432%

    No Known Activations