© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 3665
    Prev
    Next
    INDEX
    Explanations

    references to geographical regions and countries in the Middle East

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    |}{$
    -0.59
     truff
    -0.53
    getSystemService
    -0.49
     Roskov
    -0.48
     coraggio
    -0.47
    DMETHOD
    -0.47
     humaine
    -0.47
     SafeMath
    -0.46
     rimb
    -0.46
    europa
    -0.45
    POSITIVE LOGITS
     Arab
    0.97
     Saudi
    0.90
    Arab
    0.87
     Arabia
    0.86
     Arabian
    0.86
     Arabic
    0.85
     Kuwait
    0.81
     Dubai
    0.81
     ARAB
    0.80
     arabe
    0.79
    Activations Density 0.558%

    No Known Activations