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. 16-GEMMASCOPE-RES-16K
    6. 12373
    Prev
    Next
    INDEX
    Explanations

    references to Turkey and its associated cultural or geographical attributes

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

    after "Turkey", "Tur", "Cart", or "Gamma"

    np_acts-logits-general · gemini-2.0-flash

    Turkey and Cartan

    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
     tfsi
    -0.94
    AsUp
    -0.87
     linkovi
    -0.86
     Ptole
    -0.84
    XmlIgnore
    -0.84
     jedis
    -0.83
     newBuilder
    -0.81
    Traceback
    -0.80
    دانشنامهٔ
    -0.78
    tonode
    -0.77
    POSITIVE LOGITS
    Bü
    0.77
     Sut
    0.71
     Turkey
    0.67
     Lumi
    0.67
     Stur
    0.65
     Fahr
    0.65
     Tur
    0.64
     SDI
    0.64
    ніципалі
    0.62
    Turkey
    0.61
    Activations Density 0.810%

    No Known Activations