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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 16070
    Prev
    Next
    INDEX
    Explanations

    references to music categories and related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stället
    -0.76
     varandra
    -0.76
     skolan
    -0.75
     Gubernur
    -0.68
     ägg
    -0.68
     Lingkungan
    -0.67
     Umum
    -0.66
     veckan
    -0.66
     barnen
    -0.65
     kvä
    -0.65
    POSITIVE LOGITS
     ſeinen
    0.77
     pandemi
    0.75
     ſeine
    0.75
     Walkover
    0.75
     autorytatywna
    0.74
     müſſen
    0.74
     verſch
    0.73
     ſelbſt
    0.73
     geweſen
    0.73
    <unused43>
    0.72
    Activations Density 0.121%

    No Known Activations