© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 7121
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and institutions in Georgia

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

    The state of Georgia

    np_acts-logits-general · gemini-2.0-flash

    Georgia and Atlanta

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    лька
    -0.55
    databind
    -0.54
     nab
    -0.51
    Maureen
    -0.51
     Weber
    -0.50
    lam
    -0.50
    lichte
    -0.50
     Whyte
    -0.49
     DICK
    -0.49
     Richard
    -0.49
    POSITIVE LOGITS
     Georgia
    1.51
    Georgia
    1.38
     Atlanta
    1.35
     georgia
    1.30
    Atlanta
    1.30
     GEORGIA
    1.27
    LANTA
    1.26
     Tbilisi
    1.24
     Georgian
    1.24
     Emory
    1.13
    Activations Density 0.455%

    No Known Activations