© 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. 34-GEMMASCOPE-RES-16K
    11. 11385
    Prev
    Next
    INDEX
    Explanations

    specific names and references to political figures and events

    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
    fär
    -0.57
    ltä
    -0.52
    kään
    -0.47
     pistolet
    -0.47
    mäs
    -0.43
     capuz
    -0.42
     vêtement
    -0.42
     cosas
    -0.42
    bär
    -0.42
     Stirn
    -0.41
    POSITIVE LOGITS
     Brazilian
    0.93
     brazilian
    0.89
    Brazilian
    0.88
    Brazil
    0.88
    expandindo
    0.88
     Brazil
    0.88
     BRAZIL
    0.81
    brazilian
    0.79
     brazil
    0.77
     Brasil
    0.76
    Activations Density 0.583%

    No Known Activations