© 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. 22-GEMMASCOPE-RES-16K
    6. 14522
    Prev
    Next
    INDEX
    Explanations

    instances of the word "once."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "once" indicating repetition

    np_acts-logits-general · gemini-2.0-flash

    once again

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fubject
    -0.74
    marvin
    -0.72
    NewGuid
    -0.71
     myſelf
    -0.71
    saraba
    -0.69
     Monfieur
    -0.68
    RTDA
    -0.67
     purpoſe
    -0.67
     stiefel
    -0.67
    /**
    -0.67
    POSITIVE LOGITS
     upon
    1.07
     again
    1.03
     Upon
    0.95
     UPON
    0.93
    upon
    0.81
    Upon
    0.81
    again
    0.79
    Again
    0.76
     Again
    0.76
     once
    0.69
    Activations Density 0.028%

    No Known Activations