© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 13312
    Prev
    Next
    INDEX
    Explanations

    references to user-generated content or character traits

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

    certain card games or fanfiction

    np_acts-logits-general · gemini-2.0-flash

    card game mechanics and names

    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
     defaultstate
    -0.89
     الحره
    -0.75
    IndentedString
    -0.65
    rungsseite
    -0.65
     NSCoder
    -0.63
    WebServlet
    -0.61
     EconPapers
    -0.60
    сылкі
    -0.56
    MethodManager
    -0.56
    makeConstraints
    -0.54
    POSITIVE LOGITS
     Pokémon
    0.59
    GEBURTSDATUM
    0.57
     decks
    0.55
     trainer
    0.55
     trainers
    0.55
     card
    0.55
     Pokemon
    0.55
     Card
    0.53
    Pokémon
    0.53
    deck
    0.52
    Activations Density 0.176%

    No Known Activations