© 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. 959
    Prev
    Next
    INDEX
    Explanations

    concepts related to causal inference and statistical modeling

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

    Abbreviations and parenthetical citations

    np_acts-logits-general · gemini-2.0-flash

    semiparametric & machine learning terms

    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
     myſelf
    -1.69
     itſelf
    -1.69
     themſelves
    -1.56
     Jefus
    -1.40
    ^(@)
    -1.37
     himſelf
    -1.36
     Efq
    -1.28
     Monfieur
    -1.26
     houſe
    -1.26
     ſtate
    -1.25
    POSITIVE LOGITS
    sem
    0.83
    rag
    0.82
    Ã
    0.81
    vo
    0.81
    tr
    0.78
    kl
    0.78
    lo
    0.78
    una
    0.77
    df
    0.77
    ni
    0.76
    Activations Density 1.584%

    No Known Activations