© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 11676
    Prev
    Next
    INDEX
    Explanations

    the occurrence of specific numerical and scientific notation patterns

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    protoimpl
    -0.45
     pinulongan
    -0.44
    يكب
    -0.42
    enumi
    -0.42
    SourceChecksum
    -0.40
    intios
    -0.36
     parroquia
    -0.35
     continuidad
    -0.35
    LOYEES
    -0.34
    Generally
    -0.33
    POSITIVE LOGITS
     thrice
    0.88
     twice
    0.78
    Twice
    0.77
     Twice
    0.74
     times
    0.71
    twice
    0.70
     TWICE
    0.61
     zweimal
    0.60
     triple
    0.59
    times
    0.58
    Activations Density 0.522%

    No Known Activations