© 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-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 14762
    Prev
    Next
    INDEX
    Explanations

    specific geographical and place names

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

    Geographical features

    np_acts-logits-general · gemini-2.0-flash

    geographical names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Völker
    -0.29
     rač
    -0.27
     rø
    -0.26
     Öffentlichkeit
    -0.25
     orquesta
    -0.25
     الإن
    -0.25
     współ
    -0.25
     étranger
    -0.23
     medio
    -0.23
    gées
    -0.22
    POSITIVE LOGITS
     Creek
    0.99
     creek
    0.93
     Hill
    0.87
     Valley
    0.83
     Ridge
    0.79
    Creek
    0.79
     Point
    0.77
     Cove
    0.76
     Hollow
    0.75
     Farm
    0.75
    Activations Density 0.324%

    No Known Activations