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

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 5670
    Prev
    Next
    INDEX
    Explanations

    geographical locations and administrative divisions within Poland

    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
     avoient
    -0.71
     recev
    -0.69
     miniaturka
    -0.62
     pescoço
    -0.59
     fédé
    -0.59
     feroit
    -0.59
     étoient
    -0.59
     eût
    -0.58
     détect
    -0.57
     morrer
    -0.56
    POSITIVE LOGITS
     Polish
    1.02
     Poland
    1.01
    Polish
    0.97
    Poland
    0.94
     poland
    0.89
     Pologne
    0.87
     Polonia
    0.85
    polish
    0.81
     polish
    0.79
    Warsaw
    0.78
    Activations Density 0.215%

    No Known Activations