© 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. 11375
    Prev
    Next
    INDEX
    Explanations

    references to boxed elements or data structures in programming or layout contexts

    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
    usercontent
    -0.52
     PRL
    -0.47
    aturing
    -0.47
    —————
    -0.44
     <<<<<<<<<<<<<<
    -0.39
     Lerner
    -0.39
    tldr
    -0.38
     Prud
    -0.38
     Rudd
    -0.38
     Tennant
    -0.37
    POSITIVE LOGITS
     box
    2.72
     Box
    2.61
     BOX
    2.48
    Box
    2.48
    box
    2.38
     boxes
    2.31
     Boxes
    2.25
    BOX
    2.23
    Boxes
    2.06
    boxes
    1.99
    Activations Density 0.077%

    No Known Activations