Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 15698
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to machinery or processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     disambiguazione
    -0.76
    Autoritní
    -0.58
     مرئيه
    -0.56
     autorytatywna
    -0.55
     Paglinawan
    -0.51
     WaitForSeconds
    -0.51
    NewLabel
    -0.47
    hyrchwyd
    -0.47
    ỡng
    -0.46
     tắt
    -0.46
    POSITIVE LOGITS
     sekaligus
    0.48
     zugleich
    0.48
    
    0.38
     одновременно
    0.35
     cálido
    0.35
     Simultaneously
    0.35
     simultaneously
    0.34
     sambil
    0.33
     zároveň
    0.33
     AssemblyCulture
    0.32
    Activations Density 0.750%

    No Known Activations