© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14431
    Prev
    Next
    INDEX
    Explanations

    references to Nepal and related cultural or social contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Chwiliwch
    -0.78
     CanadaChoose
    -0.63
     Exactos
    -0.62
     nakalista
    -0.60
    ſelves
    -0.60
     transfieras
    -0.60
    extAlignment
    -0.59
    tagHelperRunner
    -0.58
     @"/
    -0.57
    httphttps
    -0.57
    POSITIVE LOGITS
     Nepal
    0.73
    Nepal
    0.68
     nepal
    0.56
    mandu
    0.54
    Nep
    0.54
     Kathmandu
    0.54
     Nep
    0.53
     Nepali
    0.43
     mede
    0.42
     Baumann
    0.41
    Activations Density 0.057%

    No Known Activations