© 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. 22-GEMMASCOPE-RES-16K
    11. 9798
    Prev
    Next
    INDEX
    Explanations

    instances of conjunctions that indicate continuity or connection

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

    "And" followed by a conditional/conjunctive word

    np_acts-logits-general · gemini-2.0-flash

    connective "and" starts a new clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -1.41
    aarrggbb
    -1.37
    XmlAccessType
    -1.24
    Personendaten
    -1.19
    TagMode
    -1.16
    uxxxx
    -1.16
     otomatig
    -1.13
    Autoritní
    -1.11
    SequentialGroup
    -1.09
    webElementXpaths
    -1.09
    POSITIVE LOGITS
    ,
    0.90
     while
    0.77
     if
    0.73
     yes
    0.72
     what
    0.66
     why
    0.65
     then
    0.64
     although
    0.64
    oner
    0.64
     yeah
    0.63
    Activations Density 0.149%

    No Known Activations