© 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. 10-GEMMASCOPE-RES-16K
    11. 3299
    Prev
    Next
    INDEX
    Explanations

    keywords or identifiers related to names and recognition in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    initComponents
    -0.60
     provided
    -0.51
    <tbody>
    -0.48
     select
    -0.47
     both
    -0.47
    uva
    -0.46
     south
    -0.46
    óz
    -0.45
    -
    -0.45
     consultato
    -0.45
    POSITIVE LOGITS
     ligiloj
    0.91
     Paglinawan
    0.91
     Мексичка
    0.86
     nahilalakip
    0.84
    Personendaten
    0.76
     ویکی‌پدی
    0.75
    InSection
    0.74
     فريبيس
    0.73
     lenker
    0.72
     protoimpl
    0.72
    Activations Density 0.743%

    No Known Activations