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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 8-GEMMASCOPE-RES-16K
    6. 2079
    Prev
    Next
    INDEX
    Explanations

    numerical values associated with dates or historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.72
    GEBURTSDATUM
    -0.66
     CURIAM
    -0.62
     JButton
    -0.61
    :✨
    -0.61
    Erstellt
    -0.60
    basicConfig
    -0.58
     NATION
    -0.55
     dAtA
    -0.54
     للمعارف
    -0.53
    POSITIVE LOGITS
     المعيارى
    0.91
     bisherigen
    0.62
     között
    0.61
    にかけて
    0.60
    ANIUM
    0.57
     Daarna
    0.55
     Unito
    0.55
     blijft
    0.55
     publiques
    0.54
     femininas
    0.54
    Activations Density 0.220%

    No Known Activations