© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 1988
    Prev
    Next
    INDEX
    Explanations

    references to ancient traditions and rituals associated with seasonal celebrations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    invokeLater
    -0.63
    الحياه
    -0.57
    bibfield
    -0.55
    istoitu
    -0.54
    ✨:
    -0.53
     للاسماء
    -0.53
     برانيه
    -0.52
    IntoConstraints
    -0.51
    bibinfo
    -0.50
    ucoup
    -0.50
    POSITIVE LOGITS
     ancient
    0.75
     centuries
    0.64
     древ
    0.58
     Ancient
    0.57
     civilizations
    0.56
    ancient
    0.55
     siècles
    0.53
     primitive
    0.52
    Ancient
    0.52
     millennia
    0.51
    Activations Density 0.477%

    No Known Activations