© 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-2-2B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 4937
    Prev
    Next
    INDEX
    Explanations

    instances of the word "through."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Balo
    -0.60
    berdayakan
    -0.59
     landings
    -0.59
     Sext
    -0.56
     rekord
    -0.54
     Centurion
    -0.54
     KML
    -0.53
     tart
    -0.52
    pand
    -0.51
     ActionResult
    -0.50
    POSITIVE LOGITS
     undergone
    1.05
     process
    1.03
     processes
    1.02
     undergoes
    1.02
     through
    1.00
     undergo
    0.97
     ordeal
    0.96
    through
    0.94
    Through
    0.88
    processes
    0.88
    Activations Density 0.150%

    No Known Activations