© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 8890
    Prev
    Next
    INDEX
    Explanations

    references to specific countries, particularly Iran and related geopolitical issues

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Blackwood
    -0.64
    포
    -0.63
    to
    -0.63
    Kara
    -0.62
     grammi
    -0.61
    ma
    -0.60
    p
    -0.60
    G
    -0.59
     fact
    -0.59
     Justo
    -0.58
    POSITIVE LOGITS
    WireFormatLite
    0.95
    ğından
    0.94
     تانيه
    0.94
    SceneManagement
    0.93
     NKC
    0.91
     Onion
    0.90
    存于互联网档案馆
    0.90
    bootstrapcdn
    0.90
    isissez
    0.90
     Uribe
    0.89
    Activations Density 1.153%

    No Known Activations