© 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. 2350
    Prev
    Next
    INDEX
    Explanations

    terminology related to lineage and inheritance

    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
     nastro
    -0.36
     nader
    -0.35
    гій
    -0.32
    mphony
    -0.30
     idéia
    -0.29
    astify
    -0.29
    平时
    -0.29
     anggaran
    -0.29
     województ
    -0.28
     Pauly
    -0.28
    POSITIVE LOGITS
     generations
    2.02
     inherit
    1.89
     inheritance
    1.87
     inherited
    1.81
     generational
    1.73
     legacy
    1.73
     generation
    1.65
     générations
    1.65
     herencia
    1.65
     inherits
    1.64
    Activations Density 0.689%

    No Known Activations