© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 24-GEMMASCOPE-RES-16K
    11. 6420
    Prev
    Next
    INDEX
    Explanations

    technical terms related to air conditioning systems and their components

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Air conditioning and refrigeration systems

    np_acts-logits-general · gemini-2.0-flash

    air conditioning units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Portail
    -0.58
     Италијани
    -0.55
     chó
    -0.55
    enumi
    -0.54
    endpush
    -0.53
     unknownFields
    -0.52
     zanahoria
    -0.51
    θρω
    -0.51
    queryInterface
    -0.51
    FIM
    -0.49
    POSITIVE LOGITS
     compressor
    0.78
     unit
    0.76
     condenser
    0.72
     condensing
    0.70
     refrigerant
    0.69
     units
    0.68
     evaporator
    0.68
     Split
    0.68
     split
    0.68
     Goodman
    0.67
    Activations Density 0.144%

    No Known Activations