© 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. 2-GEMMASCOPE-RES-16K
    11. 7706
    Prev
    Next
    INDEX
    Explanations

    temporal conjunctions and phrases indicating a sequence or timing of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PropertyChanging
    -0.80
    ----</
    -0.73
     BorderRadius
    -0.66
     BoxFit
    -0.65
    feinander
    -0.63
     GoogleFonts
    -0.62
    lgari
    -0.61
    Koordin
    -0.61
     gradova
    -0.59
     @"/
    -0.58
    POSITIVE LOGITS
     Incluso
    0.67
     remotely
    0.63
     Despite
    0.61
     sekal
    0.60
     Even
    0.57
    Despite
    0.57
     Though
    0.54
     Nevertheless
    0.52
     несмотря
    0.52
     siquiera
    0.51
    Activations Density 0.096%

    No Known Activations