© 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-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 846
    Prev
    Next
    INDEX
    Explanations

    terms and concepts related to MIME types and media formats

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

    after capitalized words

    np_acts-logits-general · gemini-2.0-flash

    craft creations, whitman publishing, cine media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    PerformLayout
    -0.63
    leştir
    -0.60
     censiti
    -0.60
    trom
    -0.59
     AssemblyProduct
    -0.57
    BeginInit
    -0.56
    فحة
    -0.54
     <<<<<<<<<<<<<<
    -0.53
    {?>
    -0.52
     surla
    -0.51
    POSITIVE LOGITS
    ScopeManager
    0.73
     Arquivado
    0.68
     pleaſure
    0.68
    Datuak
    0.63
    quard
    0.60
    AccessLevel
    0.59
    Worlds
    0.57
    imetsu
    0.55
     Jezus
    0.54
    eseorang
    0.54
    Activations Density 0.482%

    No Known Activations