© 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-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 2521
    Prev
    Next
    INDEX
    Explanations

    instances of the word "et," which appears to be a focal point for understanding connections or relationships in various contexts

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

    Followed by "al"

    np_acts-logits-general · gemini-2.0-flash

    et al

    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
     purpoſe
    -1.10
     pleaſure
    -1.05
     Diſ
    -1.00
     Houſe
    -1.00
     raiſ
    -0.99
     Reſ
    -0.98
     Majefty
    -0.98
     deſt
    -0.96
     houſe
    -0.95
     cauſe
    -0.94
    POSITIVE LOGITS
     al
    1.58
     Al
    0.99
    al
    0.78
     AL
    0.67
    Al
    0.64
     el
    0.54
     ал
    0.50
     als
    0.50
     alia
    0.50
     at
    0.49
    Activations Density 0.101%

    No Known Activations