© 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. 5-GEMMASCOPE-RES-16K
    11. 7183
    Prev
    Next
    INDEX
    Explanations

    verbs and related phrases indicating changes or actions involving authority and responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stata
    -0.49
     stato
    -0.49
     découver
    -0.48
     fratelli
    -0.45
    .
    -0.44
    kington
    -0.44
    richTextPanel
    -0.44
    reportWebVitals
    -0.43
     bocca
    -0.43
    っこう
    -0.42
    POSITIVE LOGITS
     autorytatywna
    0.89
    verwijspagina
    0.85
    ⓧ
    0.74
    DebuggerStep
    0.70
    platin
    0.69
    iNdEx
    0.68
    \{\\
    0.68
     ExecuteAsync
    0.66
    GEBURTSDATUM
    0.64
    PYX
    0.64
    Activations Density 0.461%

    No Known Activations