© 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 EvalsExportsAPI 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. 2763
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to cooperation and collaboration in research contexts

    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
    irited
    -0.50
     فريبيس
    -0.48
    rungsseite
    -0.44
    /*
    -0.43
    ordum
    -0.38
    RenderAtEndOf
    -0.38
    Rujuakan
    -0.37
     ffilm
    -0.37
    TagHelper
    -0.37
    лтамалар
    -0.36
    POSITIVE LOGITS
     effectively
    0.62
     perfectly
    0.58
     effectually
    0.56
    effectively
    0.53
     indirectly
    0.52
     Effectively
    0.51
     undoubtedly
    0.50
     invis
    0.49
    perfectly
    0.49
     greatly
    0.48
    Activations Density 0.169%

    No Known Activations