© 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-2-2B
    7. Residual Stream - 16k
    9. 8-GEMMASCOPE-RES-16K
    11. 9222
    Prev
    Next
    INDEX
    Explanations

    components and terms related to structures and pathways, particularly in a scientific or engineering context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    kosh
    -0.58
    Ча
    -0.57
    Mah
    -0.55
     AssemblyTitle
    -0.53
     largement
    -0.53
     factored
    -0.53
    TagMode
    -0.53
     ochi
    -0.52
    Insee
    -0.52
    setBold
    -0.51
    POSITIVE LOGITS
     corridor
    1.02
     Corridor
    0.92
     corridors
    0.91
     highway
    0.90
     pipelines
    0.89
     pipeline
    0.88
     RAIL
    0.85
    highway
    0.84
     railway
    0.84
     road
    0.83
    Activations Density 0.695%

    No Known Activations