© 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. 4390
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions, particularly related to operations and relations in equations

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

    "right" followed by specific punctuation

    np_acts-logits-general · gemini-2.0-flash

    right punctuation

    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
    NewUrlParser
    -0.61
    — 
    -0.59
    izade
    -0.58
    abes
    -0.58
    initializeApp
    -0.55
     calendriers
    -0.54
    LookAnd
    -0.54
     й
    -0.52
    Citiți
    -0.52
     Goodrich
    -0.52
    POSITIVE LOGITS
    )$
    0.69
    .$
    0.63
    ieteur
    0.59
    )
    0.59
    RTDA
    0.57
     Ucraina
    0.57
     Sodom
    0.54
     Machia
    0.54
     Perak
    0.53
     NavController
    0.53
    Activations Density 0.145%

    No Known Activations