© 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. 22-GEMMASCOPE-RES-16K
    6. 3904
    Prev
    Next
    INDEX
    Explanations

    references to Morocco and its cultural and political landscape, particularly in relation to Western Sahara

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "Morocco" or "Western Sahara"

    np_acts-logits-general · gemini-2.0-flash

    Morocco offshore oil exploration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Guatem
    -0.66
    __(/*!
    -0.61
     Guatemala
    -0.59
     propOrder
    -0.59
     Hungarian
    -0.58
     Davao
    -0.58
     Jove
    -0.58
     Irland
    -0.57
     Lithuanian
    -0.57
     Slovak
    -0.57
    POSITIVE LOGITS
     Atlas
    0.80
     Morocco
    0.80
    Mor
    0.74
     Sidi
    0.73
     North
    0.73
    Morocco
    0.72
     Mor
    0.72
     Casablanca
    0.71
     Tanger
    0.70
    Atlas
    0.69
    Activations Density 0.156%

    No Known Activations