© 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. 22-GEMMASCOPE-RES-16K
    11. 8625
    Prev
    Next
    INDEX
    Explanations

    words related to the concept of "die" or "tie"

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

    that rhyme with "die."

    np_acts-logits-general · gemini-2.0-flash

    die, tie, pie, sie, rie

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.70
    casian
    -0.64
    Vidite
    -0.64
    AMIENTO
    -0.63
     Paglinawan
    -0.63
    ("'"
    -0.63
     समीक्षक
    -0.63
    KommentareTeilen
    -0.62
    fully
    -0.60
    adə
    -0.60
    POSITIVE LOGITS
     Arie
    0.71
     pies
    0.64
     DIE
    0.62
    Rie
    0.62
    tableFuture
    0.62
    Pie
    0.61
     Trie
    0.61
     Gie
    0.59
     Hie
    0.59
     Ira
    0.59
    Activations Density 0.150%

    No Known Activations