© 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. 20-GEMMASCOPE-RES-16K
    11. 10543
    Prev
    Next
    INDEX
    Explanations

    place names and geographical references in Minnesota

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

    "Minnesota" or related terms

    np_acts-logits-general · gemini-2.0-flash

    Minneapolis and Minnesota

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DispatchToProps
    -0.61
     صوتيه
    -0.58
    interopRequire
    -0.52
    ButterKnife
    -0.50
     Ons
    -0.50
     Eastwood
    -0.49
    áng
    -0.48
    গ্রহ
    -0.48
     Jae
    -0.48
    kier
    -0.48
    POSITIVE LOGITS
     Minnesota
    1.59
    Minnesota
    1.46
     Minneapolis
    1.36
     MINNESOTA
    1.33
     MN
    1.27
     Minn
    1.23
    Minneapolis
    1.21
     Henne
    1.04
    Minn
    1.04
    MN
    1.02
    Activations Density 0.276%

    No Known Activations