© 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. 16-GEMMASCOPE-RES-16K
    11. 4568
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transition phrases that indicate conclusions or results

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

    Follows "therefore" or "hence"

    np_acts-logits-general · gemini-2.0-flash

    signals conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BrowserModule
    -0.78
    رشف
    -0.76
     OTHERWISE
    -0.76
    providedIn
    -0.72
    TagMode
    -0.70
     yourselves
    -0.65
     Monfieur
    -0.65
     FIXME
    -0.65
    welli
    -0.65
     Efq
    -0.64
    POSITIVE LOGITS
     when
    0.61
    invokeLater
    0.58
     it
    0.55
     if
    0.55
    LoadScene
    0.54
    ,
    0.54
     MenuView
    0.54
    حوالہ
    0.53
    Kjelder
    0.52
     whenever
    0.52
    Activations Density 0.417%

    No Known Activations