© 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 EvalsExportsinterp-engineNEWAPI 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. 4721
    Prev
    Next
    INDEX
    Explanations

    elements of a narrative related to geopolitical themes

    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
    forChild
    -0.37
     AssemblyProduct
    -0.34
    Дереккөздер
    -0.33
     Roumanie
    -0.31
    tadır
    -0.31
     przys
    -0.31
     micrófono
    -0.30
     Qur
    -0.30
    ariConfig
    -0.30
     Kenyan
    -0.30
    POSITIVE LOGITS
     Myanmar
    1.10
    Myanmar
    1.00
     Burmese
    0.95
     Burma
    0.90
     Aung
    0.81
    aung
    0.76
     Rango
    0.69
    Rango
    0.68
     Mandal
    0.67
    缅
    0.66
    Activations Density 0.078%

    No Known Activations