© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 10792
    Prev
    Next
    INDEX
    Explanations

    references to geographic locations and events related to conflict or violence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     الرياضيه
    -0.88
     SafeMath
    -0.60
     Koenig
    -0.57
    
    -0.51
    reportWebVitals
    -0.51
     Ritchie
    -0.51
     Lehigh
    -0.51
     تضيفلها
    -0.51
     Dunedin
    -0.49
    луй
    -0.49
    POSITIVE LOGITS
     Somalia
    1.05
     Somaliland
    1.04
     Somali
    0.99
     Punt
    0.97
    Somalia
    0.97
    Som
    0.96
     Som
    0.87
     som
    0.81
    som
    0.81
     Somal
    0.78
    Activations Density 0.079%

    No Known Activations