© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 0-GEMMASCOPE-RES-16K
    11. 9238
    Prev
    Next
    INDEX
    Explanations

    repeated phrases or motifs of the word "again."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ""){
    -0.56
    czyn
    -0.51
     Phry
    -0.50
     وتسجيلات
    -0.50
    󠁿
    -0.49
     sahiptir
    -0.49
    Билгалдахарш
    -0.48
     DEGREE
    -0.46
    Baker
    -0.46
    stan
    -0.46
    POSITIVE LOGITS
     again
    1.46
    again
    1.33
    Again
    1.11
     AGAIN
    1.10
     Again
    1.06
     novamente
    0.98
    AGAIN
    0.95
     nuevamente
    0.93
     reserve
    0.93
     lagi
    0.86
    Activations Density 0.090%

    No Known Activations