© 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. 5954
    Prev
    Next
    INDEX
    Explanations

    components and mechanisms related to air conditioning systems and vehicles

    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
     plain
    -0.40
    <i>
    -0.40
     Latin
    -0.40
     West
    -0.37
     Pop
    -0.37
     South
    -0.37
     Western
    -0.37
     Plain
    -0.37
     North
    -0.36
    干
    -0.34
    POSITIVE LOGITS
     printer
    1.35
     compressor
    1.28
     turbine
    1.24
     refrigerator
    1.20
     stove
    1.20
     reactor
    1.16
     furnace
    1.16
     carburetor
    1.15
     engine
    1.14
     impresora
    1.14
    Activations Density 0.433%

    No Known Activations