© 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. 13509
    Prev
    Next
    INDEX
    Explanations

    references to organizations and formal structures

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

    Abbreviated organization names

    np_acts-logits-general · gemini-2.0-flash

    events and actions

    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
     later
    -1.01
     recent
    -0.94
     récente
    -0.93
     später
    -0.93
     today
    -0.93
     aujourd
    -0.91
     subsequent
    -0.89
     récents
    -0.89
     tomorrow
    -0.89
     później
    -0.89
    POSITIVE LOGITS
     officially
    0.66
     formally
    0.63
    again
    0.59
     announced
    0.59
     published
    0.58
     began
    0.57
     suddenly
    0.57
     become
    0.56
     embarked
    0.56
     again
    0.56
    Activations Density 0.372%

    No Known Activations