© 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. 18-GEMMASCOPE-RES-16K
    11. 10003
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to food and cooking

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

    Abbreviations and codes

    np_acts-logits-general · gemini-2.0-flash

    technical abbreviations and codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     M
    -0.83
    M
    -0.77
     Mo
    -0.75
     Michael
    -0.73
     Moore
    -0.72
     mu
    -0.71
     million
    -0.69
    methyl
    -0.69
     methyl
    -0.68
    Mo
    -0.68
    POSITIVE LOGITS
    ########.
    0.63
     Efq
    0.62
     faſt
    0.53
     Anſ
    0.50
    pyplot
    0.50
    
    0.49
     Perſ
    0.49
     itſelf
    0.49
     Reſ
    0.48
    DispatchToProps
    0.47
    Activations Density 0.202%

    No Known Activations