© 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. 10423
    Prev
    Next
    INDEX
    Explanations

    references to comparisons and contrasts regarding conditions or qualities

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

    "for the most"

    np_acts-logits-general · gemini-2.0-flash

    for the most part

    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
     AssemblyCulture
    -0.65
     calendriers
    -0.61
     betweenstory
    -0.59
    AlterField
    -0.57
    čkou
    -0.57
    IBAction
    -0.56
    NgModule
    -0.55
    GEBURTS
    -0.55
    
    -0.55
     AssemblyTitle
    -0.55
    POSITIVE LOGITS
     generally
    2.22
     mostly
    2.09
    generally
    1.99
    mostly
    1.90
    Generally
    1.87
     Generally
    1.86
    Mostly
    1.86
     Mostly
    1.83
     largely
    1.71
     mainly
    1.63
    Activations Density 0.520%

    No Known Activations