© 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. 7845
    Prev
    Next
    INDEX
    Explanations

    geographical locations and specific entities related to places

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

    Locations in cold regions

    np_acts-logits-general · gemini-2.0-flash

    Alaska, Arctic, Labrador, Winter War

    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
     Enugu
    -0.59
     Warwickshire
    -0.56
     Telugu
    -0.54
     elegans
    -0.53
     Burundi
    -0.51
     Telangana
    -0.51
     Monmouth
    -0.51
     Coventry
    -0.50
     django
    -0.50
     Indore
    -0.49
    POSITIVE LOGITS
     Alaska
    1.28
     Arctic
    1.22
     Alaskan
    1.19
    Alaska
    1.17
     arctic
    1.13
    Arctic
    1.11
     alaska
    1.04
     tundra
    1.04
    arctic
    1.03
     Fairbanks
    0.98
    Activations Density 0.161%

    No Known Activations