© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 18-GEMMASCOPE-RES-16K
    11. 15795
    Prev
    Next
    INDEX
    Explanations

    references to conjunctions and logical connectors in the text

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

    "and" or "or" followed by a word

    np_acts-logits-general · gemini-2.0-flash

    any or all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UnusedPrivate
    -0.54
     ExecuteAsync
    -0.53
    ViewFeatures
    -0.52
     Toibin
    -0.51
    invokeLater
    -0.51
    SupportActionBar
    -0.51
    hadoop
    -0.50
    ագրություններ
    -0.50
    dolu
    -0.50
    Referencies
    -0.48
    POSITIVE LOGITS
     Theſe
    0.72
     greateſt
    0.64
    ſelf
    0.62
     ſever
    0.61
     ſeveral
    0.61
     Eſ
    0.61
     beſt
    0.61
     RIPRODUZIONE
    0.61
     Monfieur
    0.60
     Beſ
    0.59
    Activations Density 0.235%

    No Known Activations