© 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. 41-GEMMASCOPE-RES-16K
    11. 7093
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to programming and algorithm functionality

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 41-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_41/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.41.hook_resid_post
    Hook Layer
    41
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     weren
    -0.38
    摇了摇头
    -0.36
     szüks
    -0.36
    expandindo
    -0.35
    点了点头
    -0.34
     themſelves
    -0.34
     vectorielles
    -0.33
    ußt
    -0.33
     pleaſure
    -0.32
    Sucesor
    -0.32
    POSITIVE LOGITS
     gets
    1.63
     sends
    1.61
     creates
    1.60
     takes
    1.60
     develops
    1.58
     gives
    1.57
     delivers
    1.55
     learns
    1.52
     performs
    1.52
     finds
    1.52
    Activations Density 4.122%

    No Known Activations