© 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. 10838
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to image processing and analysis in astrophysical contexts

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

    preceding "maps" or related to "maps"

    np_acts-logits-general · gemini-2.0-flash

    reconstructed maps

    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
     QtCore
    -0.57
     MainAxisSize
    -0.48
     SqlConnection
    -0.42
    ArgsConstructor
    -0.42
    inSlope
    -0.41
    μβρίου
    -0.40
     SqlCommand
    -0.40
    AsUp
    -0.40
    IBarButtonItem
    -0.39
    makeConstraints
    -0.39
    POSITIVE LOGITS
     maps
    0.72
     image
    0.72
     map
    0.71
     images
    0.69
     Map
    0.62
    map
    0.61
     Image
    0.60
    Map
    0.58
    image
    0.58
     Images
    0.58
    Activations Density 0.674%

    No Known Activations