© 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. 15967
    Prev
    Next
    INDEX
    Explanations

    instances of formatted mathematical alignments in equations

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

    Strings starting with "\begin{aligned}"

    np_acts-logits-general · gemini-2.0-flash

    aligned block delimiters

    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
    NameInMap
    -0.79
     Roskov
    -0.67
    protoimpl
    -0.60
    titleMargin
    -0.58
    lungen
    -0.56
    Tazama
    -0.53
    autique
    -0.53
    drawSprites
    -0.53
    しくは
    -0.53
    (!__
    -0.52
    POSITIVE LOGITS
    httphttps
    0.57
    UserScript
    0.57
    HostException
    0.56
    AddRef
    0.56
    ObjectContext
    0.51
     Seeder
    0.50
    owohl
    0.49
    GINIA
    0.49
    cologist
    0.48
     RemoteException
    0.48
    Activations Density 0.043%

    No Known Activations