© 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. 35-GEMMASCOPE-RES-16K
    11. 14955
    Prev
    Next
    INDEX
    Explanations

    references to the United States, indicating a focus on American entities and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Lingkungan
    -0.44
    guiente
    -0.43
     amado
    -0.42
     cárcel
    -0.41
    animaux
    -0.40
     peligro
    -0.40
     lingkungan
    -0.40
     peines
    -0.39
    camisetas
    -0.39
     Konsequ
    -0.39
    POSITIVE LOGITS
     States
    0.91
     Kingdom
    0.82
     Nations
    0.74
     kingdom
    0.70
    States
    0.69
    Kingdom
    0.66
     states
    0.64
     KINGDOM
    0.63
    kingdom
    0.61
     United
    0.60
    Activations Density 0.152%

    No Known Activations