© 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. 0-GEMMASCOPE-RES-16K
    11. 2550
    Prev
    Next
    INDEX
    Explanations

    references to formal events or ceremonies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     duide
    -0.42
    zis
    -0.40
    sidemargin
    -0.40
     broek
    -0.39
     pener
    -0.37
    mybatisplus
    -0.35
     reason
    -0.35
     AssemblyCulture
    -0.35
     moeite
    -0.35
     leiding
    -0.34
    POSITIVE LOGITS
     ceremony
    1.81
     ceremonies
    1.73
     celebration
    1.59
     Ceremony
    1.57
     celebrations
    1.55
     celebratory
    1.53
     ceremonial
    1.52
     celebrating
    1.47
    celebr
    1.45
     celebrate
    1.43
    Activations Density 1.689%

    No Known Activations