© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 8793
    Prev
    Next
    INDEX
    Explanations

    mathematical constructs and concepts related to complex analysis and linear algebra

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     NgModule
    -0.52
    arangay
    -0.49
    Fatalf
    -0.49
    ſtand
    -0.49
    ंदीखरीदारी
    -0.48
    kulum
    -0.47
     Disposition
    -0.46
    reda
    -0.46
    DataSetChanged
    -0.45
    uttore
    -0.45
    POSITIVE LOGITS
    mitian
    0.61
     propOrder
    0.45
    createCell
    0.44
    IsContent
    0.42
    XMLSchema
    0.39
     referenties
    0.36
     Geheim
    0.35
     galería
    0.34
    astéroïdes
    0.34
     Gläub
    0.32
    Activations Density 1.051%

    No Known Activations