© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 39-GEMMASCOPE-RES-16K
    6. 2253
    Prev
    Next
    INDEX
    Explanations

    references to cultural or religious celebrations and significant events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    戬
    -0.38
     bolos
    -0.37
     kasarigan
    -0.35
    Werdegang
    -0.33
     Auft
    -0.33
     empuj
    -0.33
    ADUATE
    -0.32
    illable
    -0.32
     bluntly
    -0.32
     Umständen
    -0.31
    POSITIVE LOGITS
     felic
    0.72
     Interaction
    0.69
     felicit
    0.67
     interaction
    0.66
    Interaction
    0.65
     interacted
    0.65
    Felic
    0.64
     interacts
    0.61
     Felic
    0.60
    interaction
    0.59
    Activations Density 0.144%

    No Known Activations