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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 16-GEMMASCOPE-RES-16K
    6. 8951
    Prev
    Next
    INDEX
    Explanations

    terms related to food selections and cultural dining experiences

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

    Location within a country

    np_acts-logits-general · gemini-2.0-flash

    country or national organizations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ждународ
    -0.62
    KommentareTeilen
    -0.62
    Welt
    -0.51
    EntryPoint
    -0.51
    unehmen
    -0.51
    RectangleBorder
    -0.50
    MotionEvent
    -0.49
    SupportActionBar
    -0.49
    ędzynarod
    -0.48
    uslar
    -0.47
    POSITIVE LOGITS
     country
    0.84
     país
    0.75
     landet
    0.71
     nation
    0.69
     nacional
    0.68
     countrymen
    0.68
    بوابة
    0.66
    country
    0.65
     national
    0.65
     brasileiro
    0.64
    Activations Density 0.491%

    No Known Activations