© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 11021
    Prev
    Next
    INDEX
    Explanations

    phrases related to geological and geographical features and their interactions

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

    Movement from water to land

    np_acts-logits-general · gemini-2.0-flash

    land from water

    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
    mergeFrom
    -0.33
     linkovi
    -0.31
     createSprite
    -0.31
     electronic
    -0.30
     scatola
    -0.30
     Broder
    -0.29
     Sam
    -0.28
     transparence
    -0.28
    medium
    -0.28
     [*]
    -0.28
    POSITIVE LOGITS
     mainland
    1.85
     ashore
    1.84
     onshore
    1.48
     Mainland
    1.44
     shore
    1.41
     land
    1.27
     inland
    1.23
     continental
    1.22
    shore
    1.10
    大陆
    1.10
    Activations Density 0.179%

    No Known Activations