© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 4434
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and processes

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

    Follows adverbs of simplicity

    np_acts-logits-general · gemini-2.0-flash

    simply, just, only

    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
     also
    -0.68
     especially
    -0.55
    DotNetBar
    -0.51
     precisely
    -0.51
     ALSO
    -0.51
    Also
    -0.51
     '\\;'
    -0.50
     particularly
    -0.50
     myös
    -0.50
     auch
    -0.49
    POSITIVE LOGITS
     saja
    0.96
    而已
    0.89
     thôi
    0.88
    单纯
    0.88
     simplement
    0.85
    simply
    0.84
     suffit
    0.82
     Simplemente
    0.80
     basta
    0.80
     semplici
    0.80
    Activations Density 0.306%

    No Known Activations