© 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. 1347
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and establishments within Georgia

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

    Followed by digits

    np_acts-logits-general · gemini-2.0-flash

    georgia and tbilisi

    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
    amboo
    -0.49
    ALLE
    -0.49
    ოლი
    -0.46
     nî
    -0.45
    copo
    -0.42
     patro
    -0.41
     mau
    -0.41
     kém
    -0.41
    FileOutputStream
    -0.41
    ()?;
    -0.40
    POSITIVE LOGITS
     Georgian
    0.94
     Tbilisi
    0.93
     Georgia
    0.84
    ashvili
    0.84
     GEORGIA
    0.81
     Gior
    0.78
     georgia
    0.76
    Georgia
    0.75
    bilisi
    0.73
    Georg
    0.70
    Activations Density 0.057%

    No Known Activations