© 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. 15-GEMMASCOPE-RES-16K
    11. 6325
    Prev
    Next
    INDEX
    Explanations

    requirements and formal specifications within technical or legal contexts

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    JoinColumn
    -0.40
     Air
    -0.40
     symmetrical
    -0.40
     Bailly
    -0.40
    Daily
    -0.39
     airbag
    -0.38
     Daily
    -0.38
    บุ
    -0.38
    air
    -0.38
     Recipro
    -0.37
    POSITIVE LOGITS
    ContentAsync
    0.93
    GEBURTSDATUM
    0.86
     nahilalakip
    0.86
    Datuak
    0.78
     informée
    0.75
    httphttps
    0.75
    MemoryWarning
    0.73
     незавершена
    0.67
    Personendaten
    0.67
    ंदीखरीदारी
    0.65
    Activations Density 0.251%

    No Known Activations