Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3022
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and their characteristics

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

    preceding the names of capitals

    np_acts-logits-general · gemini-2.0-flash

    national, provincial, regional capitals

    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
    бята
    -0.48
    xer
    -0.45
     विश्वसनीयता
    -0.39
     समीक्षाएं
    -0.39
     조
    -0.36
    XmlElement
    -0.35
    조
    -0.34
     церковь
    -0.33
    IMENTS
    -0.33
    groep
    -0.33
    POSITIVE LOGITS
     capital
    2.23
    capital
    1.84
     capitale
    1.76
     Capital
    1.71
     CAPITAL
    1.66
    Capital
    1.65
     capitals
    1.63
     capitol
    1.58
     capitales
    1.51
    CAPITAL
    1.43
    Activations Density 0.153%

    No Known Activations