© 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. 7383
    Prev
    Next
    INDEX
    Explanations

    references to specific events and their timing

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

    Numerical identifier followed by context

    np_acts-logits-general · gemini-2.0-flash

    editions and installments

    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
     lately
    -0.92
     recentemente
    -0.90
     recently
    -0.90
    Recently
    -0.87
     today
    -0.87
     Recently
    -0.85
     amanhã
    -0.85
     yesterday
    -0.79
     recientemente
    -0.78
    recently
    -0.77
    POSITIVE LOGITS
     edition
    1.17
     iteration
    1.01
    edition
    0.90
     installment
    0.88
     batch
    0.86
     incarnation
    0.84
     editions
    0.82
     instalment
    0.77
     crop
    0.76
     version
    0.76
    Activations Density 0.190%

    No Known Activations