© 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. 3-GEMMASCOPE-RES-16K
    11. 5495
    Prev
    Next
    INDEX
    Explanations

    phrases indicating a position of prominence or superiority

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -0.48
    instancetype
    -0.45
    Tembelea
    -0.45
    niająca
    -0.42
     donors
    -0.41
    úgó
    -0.40
     crashes
    -0.40
     disasters
    -0.40
     rozum
    -0.40
     unknowns
    -0.39
    POSITIVE LOGITS
     periodic
    1.10
     Periodic
    1.08
     characteristic
    1.06
    periodic
    1.02
    Periodic
    1.00
    characteristic
    0.94
     Characteristic
    0.93
    Characteristic
    0.92
     leading
    0.91
    Leading
    0.90
    Activations Density 0.081%

    No Known Activations