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. 2436
    Prev
    Next
    INDEX
    Explanations

    geographical locations and nationalities

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

    Country or region names

    np_acts-logits-general · gemini-2.0-flash

    countries and nationals

    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
    />";
    -0.80
    〢
    -0.71
    enderror
    -0.70
    addContainerGap
    -0.68
     disponibilités
    -0.67
    ']));
    -0.67
     IBOutlet
    -0.65
    wój
    -0.65
    ürtel
    -0.64
    +#+#
    -0.63
    POSITIVE LOGITS
     nationals
    0.58
     national
    0.56
     voisin
    0.50
     appuy
    0.46
     country
    0.46
    ian
    0.46
     gospod
    0.45
    SOUNDBITE
    0.45
     vois
    0.44
    ’
    0.43
    Activations Density 0.386%

    No Known Activations