© 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. 9-GEMMASCOPE-RES-16K
    11. 8443
    Prev
    Next
    INDEX
    Explanations

    keywords related to drag-and-drop functionality in programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    umumkan
    -0.44
     którzy
    -0.43
    openConnection
    -0.43
     oprot
    -0.43
     newOwner
    -0.43
    Біографія
    -0.42
     kepad
    -0.40
    quiao
    -0.40
    ]")]
    -0.39
     SqlCommand
    -0.39
    POSITIVE LOGITS
     drag
    1.49
     Drag
    1.38
    Drag
    1.33
    drag
    1.29
     dragging
    1.24
     drags
    1.16
     dragged
    1.14
     DRAG
    1.13
    dragging
    1.01
    Dragging
    0.97
    Activations Density 0.248%

    No Known Activations