© 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. 5800
    Prev
    Next
    INDEX
    Explanations

    questions and inquiries about specific details or clarifications

    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
    Their
    -1.80
     their
    -1.68
    their
    -1.66
    彼らの
    -1.56
     Their
    -1.55
     их
    -1.50
    他们的
    -1.48
    Их
    -1.46
     leur
    -1.45
    他們的
    -1.44
    POSITIVE LOGITS
     they
    1.27
     они
    0.62
     তার
    0.62
     thay
    0.62
     वे
    0.59
     zij
    0.56
    hey
    0.54
     вони
    0.52
     وہ
    0.52
     dey
    0.51
    Activations Density 0.500%

    No Known Activations