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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 6540
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and regional features

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

    Welsh locations and names

    np_acts-logits-general · gemini-2.0-flash

    welsh place names

    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
     McPherson
    -0.64
     Pease
    -0.62
     Bulgar
    -0.60
     Danube
    -0.59
     Missoula
    -0.57
     Macedonian
    -0.56
     Ried
    -0.55
     Mississauga
    -0.54
     Kula
    -0.54
     Olms
    -0.53
    POSITIVE LOGITS
     Welsh
    1.64
    Welsh
    1.49
    Wales
    1.45
     Wales
    1.44
     Cardiff
    1.37
     Cymru
    1.29
    Cardiff
    1.26
    wales
    1.17
     wales
    1.13
     Swansea
    1.09
    Activations Density 0.221%

    No Known Activations