© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 33-GEMMASCOPE-RES-16K
    11. 963
    Prev
    Next
    INDEX
    Explanations

    references to spatial arrangements or central focal points in a context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    gnon
    -0.30
    StoryboardSegue
    -0.30
     ni
    -0.29
    meny
    -0.29
     آذ
    -0.29
     mengg
    -0.28
    MenuView
    -0.27
    cosis
    -0.27
     aparte
    -0.27
    一提
    -0.27
    POSITIVE LOGITS
     center
    2.50
     centre
    2.42
     central
    2.03
    centre
    1.98
    center
    1.97
     centro
    1.95
    中心
    1.91
     CENTER
    1.87
     pusat
    1.79
     centrally
    1.79
    Activations Density 0.624%

    No Known Activations