© 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. 20-GEMMASCOPE-RES-16K
    11. 4439
    Prev
    Next
    INDEX
    Explanations

    sequences of letters and symbols resembling programming functions or code

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

    Follows currency codes or short abbreviations

    np_acts-logits-general · gemini-2.0-flash

    food ingredients

    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
    Ber
    -0.45
    eben
    -0.43
    бен
    -0.43
    ign
    -0.43
    GH
    -0.42
     Ber
    -0.42
    fer
    -0.42
     senso
    -0.40
    ber
    -0.40
    I
    -0.39
    POSITIVE LOGITS
    mybatisplus
    0.97
    出版年
    0.97
    Personensuche
    0.96
     nakalista
    0.96
    省市镇
    0.94
     propOrder
    0.90
     '\\;'
    0.90
    ंदीखरीदारी
    0.89
    GEBURTSDATUM
    0.81
     Roskov
    0.81
    Activations Density 0.117%

    No Known Activations