© 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. 11-GEMMASCOPE-RES-16K
    6. 7953
    Prev
    Next
    INDEX
    Explanations

    terms related to the Green Party and its political context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     renovables
    -0.36
     compi
    -0.35
     Picchu
    -0.35
    AlterField
    -0.35
    ValueGeneration
    -0.34
     Sic
    -0.34
    SharedDtor
    -0.33
    뜨
    -0.32
     sic
    -0.32
    <table>
    -0.31
    POSITIVE LOGITS
    tanleria
    0.55
    Tikang
    0.53
     coalition
    0.50
    Życiorys
    0.49
     party
    0.48
    ništ
    0.47
    alga
    0.47
    WithIdentifier
    0.46
    الحياه
    0.46
     Party
    0.46
    Activations Density 0.387%

    No Known Activations