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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 36-GEMMASCOPE-RES-16K
    11. 7885
    Prev
    Next
    INDEX
    Explanations

    patterns and symbols related to numerical data or calculations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     PRS
    -0.34
    у
    -0.32
     مؤس
    -0.32
    tagHelper
    -0.31
    фф
    -0.31
    搭
    -0.30
    ZZLE
    -0.30
    —————
    -0.29
    ങ്
    -0.29
     Fürst
    -0.29
    POSITIVE LOGITS
     '\\;'
    0.57
    rxjs
    0.54
     lenker
    0.54
    providedIn
    0.53
    uxxxx
    0.52
     հղումներ
    0.52
    เกง
    0.52
     ویکی‌پدی
    0.49
    ImageContext
    0.48
     Paglinawan
    0.48
    Activations Density 0.518%

    No Known Activations