© 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. 11610
    Prev
    Next
    INDEX
    Explanations

    significant quotes or statements in conversational contexts

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

    Follows a verb "to be"

    np_acts-logits-general · gemini-2.0-flash

    was good, I said, she doesn, more than

    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
     portanto
    -0.92
     Indeed
    -0.89
    Indeed
    -0.84
    indeed
    -0.83
     Importantly
    -0.81
     Whilst
    -0.78
     precisely
    -0.75
     indeed
    -0.75
    Whilst
    -0.75
     Notably
    -0.74
    POSITIVE LOGITS
     
    0.70
     defaultstate
    0.69
    .*")]
    0.68
    ResumeLayout
    0.65
     surla
    0.62
    SBATCH
    0.61
     (
    0.61
     ویکی‌پدیا
    0.61
     everybody
    0.60
     beginnetje
    0.59
    Activations Density 0.253%

    No Known Activations