© 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. 18-GEMMASCOPE-RES-16K
    11. 91
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and organizational structures in industry contexts

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

    Location words after "in" or "throughout"

    np_acts-logits-general · gemini-2.0-flash

    geographical locations after 'in'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Haitian
    -0.63
     Etrus
    -0.62
     Berliner
    -0.58
     Algerian
    -0.57
     Macedonian
    -0.57
     Tasmanian
    -0.57
     Florentine
    -0.56
     Athenian
    -0.55
    Welsh
    -0.55
     Flinders
    -0.55
    POSITIVE LOGITS
     Europe
    1.13
     England
    1.04
     India
    1.02
     France
    0.98
     Britain
    0.94
     Australia
    0.93
     Canada
    0.93
     Japan
    0.91
     Germany
    0.91
     Italy
    0.91
    Activations Density 0.575%

    No Known Activations