© 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. 24-GEMMASCOPE-RES-16K
    11. 4879
    Prev
    Next
    INDEX
    Explanations

    numerical values and percentages

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

    Numbers after "1" or "one"

    np_acts-logits-general · gemini-2.0-flash

    numbers and 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
     disambiguazione
    -0.83
    CloseOperation
    -0.81
     Clauses
    -0.68
    rungsseite
    -0.68
     branches
    -0.67
     potes
    -0.67
     cations
    -0.66
    MessageTagHelper
    -0.66
     évek
    -0.65
     microns
    -0.64
    POSITIVE LOGITS
     unit
    0.72
     attentes
    0.66
     week
    0.63
     bénéfices
    0.62
     négociations
    0.61
     églises
    0.60
     hour
    0.60
     episode
    0.58
     person
    0.58
     vœux
    0.56
    Activations Density 0.373%

    No Known Activations