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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 11175
    Prev
    Next
    INDEX
    Explanations

    themes related to power and domination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/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.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mußten
    -0.39
     Grüsse
    -0.38
    envolvimento
    -0.38
     său
    -0.36
     gesamte
    -0.35
    《
    -0.34
    werben
    -0.34
     fuese
    -0.34
     supposedly
    -0.34
     hubieran
    -0.33
    POSITIVE LOGITS
    ymce
    0.62
     newOwner
    0.61
    RegressionTest
    0.60
     pylint
    0.60
     queſta
    0.59
     itemView
    0.55
    WebVitals
    0.54
    
    0.54
    liken
    0.54
    ésultats
    0.53
    Activations Density 0.116%

    No Known Activations