© 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. 18-GEMMASCOPE-RES-16K
    11. 2171
    Prev
    Next
    INDEX
    Explanations

    phrases that imply comparison or contrast

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

    Comparison to something ordinary

    np_acts-logits-general · gemini-2.0-flash

    ordinary comparison

    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
    setVerticalGroup
    -0.75
    kloped
    -0.70
     ModelExpression
    -0.69
    WebServlet
    -0.62
    SuppressMessage
    -0.56
    NEVER
    -0.55
    Parcelize
    -0.55
    jspx
    -0.55
    EndGlobalSection
    -0.53
     resourceCulture
    -0.53
    POSITIVE LOGITS
     ordinary
    1.51
     merely
    1.42
     simply
    1.39
     mere
    1.33
    ordinary
    1.32
    ただの
    1.26
    普通的
    1.25
     zwyk
    1.22
     просто
    1.17
     Ordinary
    1.17
    Activations Density 0.297%

    No Known Activations