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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 10693
    Prev
    Next
    INDEX
    Explanations

    references to various economic or social sectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pli
    -0.85
     Appropriation
    -0.83
     McLaughlin
    -0.81
    ableness
    -0.80
     Dn
    -0.80
     Pli
    -0.79
    ethene
    -0.77
     Geraldine
    -0.76
     DMD
    -0.76
     Appropriations
    -0.75
    POSITIVE LOGITS
     SECTOR
    1.36
     sectors
    1.27
     Sector
    1.26
     Sectors
    1.25
     sector
    1.23
    SECTOR
    1.14
    Sector
    1.07
    sectors
    1.05
    sector
    1.04
    Sectors
    1.01
    Activations Density 0.119%

    No Known Activations