© 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-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 11372
    Prev
    Next
    INDEX
    Explanations

    references to Iran and associated political dynamics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     newArray
    -0.86
     Jefus
    -0.84
    BrowserModule
    -0.83
     Chrift
    -0.81
     Hül
    -0.79
     Alquiler
    -0.77
    ALLY
    -0.76
    ttemberg
    -0.73
    cely
    -0.71
    ally
    -0.71
    POSITIVE LOGITS
     Iran
    1.10
     Irán
    1.08
    Iran
    0.95
     Iranian
    0.90
     IR
    0.86
     iran
    0.83
     Gibb
    0.82
    Iranian
    0.81
     rasp
    0.79
    IsContent
    0.79
    Activations Density 0.602%

    No Known Activations