© 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. 1-GEMMASCOPE-RES-16K
    11. 2608
    Prev
    Next
    INDEX
    Explanations

    parts and features related to automotive technology, specifically those involving wheels and steering components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DotNetBar
    -0.42
     Walkover
    -0.41
     Dans
    -0.40
     Arca
    -0.39
     Jr
    -0.39
     Mila
    -0.38
     transported
    -0.38
    makeText
    -0.38
     Glor
    -0.38
     Bru
    -0.38
    POSITIVE LOGITS
     wheel
    1.15
     nozzle
    1.10
     flywheel
    1.09
     valve
    1.09
     pistons
    1.06
     pulley
    1.05
     piston
    1.04
     crankshaft
    1.04
     impeller
    1.02
     shaft
    1.02
    Activations Density 0.455%

    No Known Activations