© 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. 6041
    Prev
    Next
    INDEX
    Explanations

    formal and structured segments of written content, particularly those involving documentation and reviews

    oai_token-act-pair · gpt-4o-miniTriggered 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
    Not in Any Lists

    No Comments

    Negative Logits
    ثيق
    -0.43
    lovakia
    -0.37
     AppCompatTheme
    -0.35
     blow
    -0.32
     goog
    -0.32
    outState
    -0.28
     MenuView
    -0.28
    Reader
    -0.28
     delivery
    -0.28
    Trama
    -0.27
    POSITIVE LOGITS
    oredCriteria
    0.84
    PREVIOUS
    0.67
    XmlAccessType
    0.58
    previously
    0.55
     utafitiHapana
    0.52
    Personendaten
    0.51
     anteriormente
    0.51
     onCancelled
    0.51
    Previously
    0.50
    ouncements
    0.50
    Activations Density 0.903%

    No Known Activations