© 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 EvalsExportsAPI 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. 11384
    Prev
    Next
    INDEX
    Explanations

    locations and geographical descriptions

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

    preceding "is located" or location

    np_acts-logits-general · gemini-2.0-flash

    describes location

    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
    Congo
    -0.36
     bi
    -0.35
    usei
    -0.34
    pius
    -0.34
    +#+
    -0.33
    bootstrapcdn
    -0.33
     pinulongan
    -0.33
     curd
    -0.33
    用到
    -0.31
    ╝
    -0.31
    POSITIVE LOGITS
     located
    2.66
     Located
    2.39
    Located
    2.33
    located
    2.30
     situated
    2.17
     Situated
    1.91
     ubicado
    1.91
    Situated
    1.89
     location
    1.85
     situé
    1.83
    Activations Density 0.745%

    No Known Activations