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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65824
    Prev
    Next
    INDEX
    Explanations

    references to hierarchical structures and ceremonial arrangements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     currentUser
    -0.30
    printStats
    -0.30
     ecological
    -0.28
     plomb
    -0.28
    Vapour
    -0.28
    erschrank
    -0.28
    steamcommunity
    -0.27
    LastError
    -0.27
    nextProps
    -0.27
     veder
    -0.26
    POSITIVE LOGITS
     tables
    0.94
     chairs
    0.85
     makeshift
    0.84
     aisles
    0.84
     rows
    0.82
     semicirc
    0.81
     seating
    0.79
     tents
    0.77
     sillas
    0.76
     sofas
    0.76
    Activations Density 0.029%

    No Known Activations