© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 6392
    Prev
    Next
    INDEX
    Explanations

    mentions of sporting events and their outcomes

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

    Scores or victories

    np_acts-logits-general · gemini-2.0-flash

    victory, loss, defeat, win

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Kjelder
    -0.59
    әрмәләр
    -0.57
    BeginContext
    -0.56
    🟤
    -0.55
     otomatig
    -0.53
    posedge
    -0.53
    MemoryWarning
    -0.52
    BASEPATH
    -0.52
    stalt
    -0.51
     NSCoder
    -0.51
    POSITIVE LOGITS
    Diweddarwch
    0.38
    TintMode
    0.34
     elég
    0.32
     victory
    0.32
     pecados
    0.31
    richTextPanel
    0.31
     verdict
    0.30
    destroyAll
    0.30
    ➟
    0.29
    ish
    0.29
    Activations Density 0.107%

    No Known Activations