© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 1778
    Prev
    Next
    INDEX
    Explanations

    proper names and titles of individuals, particularly in the context of art and military

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

    following names of Russian people

    np_acts-logits-general · gemini-2.0-flash

    Russian names and citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     lenker
    -0.60
    SpringBootTest
    -0.48
    buc
    -0.44
     Wikispecies
    -0.44
    ãng
    -0.44
    НОСТИ
    -0.43
    cí
    -0.43
    tanleria
    -0.43
    weck
    -0.43
    onerror
    -0.42
    POSITIVE LOGITS
     Roskov
    0.73
    writeFieldEnd
    0.68
    yntaxException
    0.66
    Geplaatst
    0.61
     Andree
    0.60
     sidor
    0.60
     Ivanov
    0.60
    ItemBackground
    0.58
     Perfil
    0.58
     Alexey
    0.57
    Activations Density 0.202%

    No Known Activations