© 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. 4-GEMMASCOPE-RES-16K
    11. 1390
    Prev
    Next
    INDEX
    Explanations

    words indicating composition or structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     consistent
    -0.83
    #>
    -0.69
    consistent
    -0.68
     rekening
    -0.66
     parem
    -0.64
     Klagen
    -0.64
     sobra
    -0.64
     Consistent
    -0.64
     QLabel
    -0.62
     roh
    -0.60
    POSITIVE LOGITS
     consists
    1.23
     consisted
    1.17
     consisting
    1.09
     consist
    0.94
     terdiri
    0.94
    sists
    0.84
     Hecht
    0.78
    setopt
    0.78
     zi
    0.76
     démocr
    0.75
    Activations Density 0.085%

    No Known Activations