© 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. 20-GEMMASCOPE-RES-16K
    11. 11213
    Prev
    Next
    INDEX
    Explanations

    terms related to the concept of 'decimation' or 'removal'

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

    The token "Dec" or "dec"

    np_acts-logits-general · gemini-2.0-flash

    words beginning with Dec

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    uegos
    -0.63
     châ
    -0.54
    iress
    -0.50
     poudre
    -0.50
     mayores
    -0.50
    mlar
    -0.49
    ometr
    -0.47
    äsident
    -0.46
    freude
    -0.46
     configureStore
    -0.46
    POSITIVE LOGITS
     Dec
    0.81
    dec
    0.80
    Dec
    0.80
     Oct
    0.76
    Oct
    0.72
     invokingState
    0.71
     dec
    0.70
     Aug
    0.70
     Jul
    0.66
     OCT
    0.66
    Activations Density 0.150%

    No Known Activations