© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 360
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and specific sites of scientific interest

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

    Cambridge, Anglia, or East of England locations

    np_acts-logits-general · gemini-2.0-flash

    Cambridge

    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
    ftagPool
    -0.62
     Zahn
    -0.60
    헌
    -0.59
     protoimpl
    -0.59
    StoryboardSegue
    -0.58
     Soni
    -0.58
    UnsafeEnabled
    -0.58
     biografias
    -0.57
    dafx
    -0.57
    IRQn
    -0.55
    POSITIVE LOGITS
     Cambridge
    0.98
    Cambridge
    0.89
     Norwich
    0.86
     Norfolk
    0.78
    Norfolk
    0.77
    Camb
    0.73
     Camb
    0.72
     Newmarket
    0.72
     Anglia
    0.71
     camb
    0.67
    Activations Density 0.150%

    No Known Activations