© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 7814
    Prev
    Next
    INDEX
    Explanations

    references to significant events and announcements in life and media

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    UrlResolution
    -0.71
    othelioma
    -0.53
    lems
    -0.52
    GillaGilla
    -0.51
    topus
    -0.51
     ſind
    -0.50
    Contacto
    -0.50
    ſcher
    -0.49
     contacts
    -0.49
    kegaard
    -0.49
    POSITIVE LOGITS
    Fans
    0.75
     fans
    0.75
     Fans
    0.71
    Speaking
    0.64
     Speaking
    0.63
    fans
    0.63
     Earlier
    0.60
     reportedly
    0.59
     Meanwhile
    0.58
     meanwhile
    0.58
    Activations Density 0.139%

    No Known Activations