© 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. 15-GEMMASCOPE-RES-16K
    11. 1907
    Prev
    Next
    INDEX
    Explanations

    events related to player transfers and debuts in sports

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Diweddarwch
    -0.82
    :✨
    -0.68
     autorytatywna
    -0.65
    ftagPool
    -0.65
     plufieurs
    -0.64
    LookAnd
    -0.63
     affitto
    -0.60
     setOpen
    -0.60
    GTCX
    -0.59
     noDo
    -0.58
    POSITIVE LOGITS
     returned
    0.40
     be
    0.40
     subsequent
    0.39
     
    0.38
     again
    0.37
     return
    0.36
     promoted
    0.36
     thereafter
    0.35
     shortly
    0.35
     then
    0.35
    Activations Density 0.633%

    No Known Activations