© 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. 33-GEMMASCOPE-RES-16K
    11. 5747
    Prev
    Next
    INDEX
    Explanations

    specific scientific terminology related to neurotransmitters and neurobiology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.44
    CloseOperation
    -0.43
     cylinders
    -0.41
     diplomacy
    -0.39
     bluz
    -0.37
    겉
    -0.37
     cylinder
    -0.37
    physiology
    -0.36
     physiology
    -0.36
    Leggi
    -0.36
    POSITIVE LOGITS
    atorial
    0.75
    isional
    0.68
    neurial
    0.68
    sonian
    0.65
    arial
    0.65
    sianic
    0.65
    osomal
    0.65
    orphic
    0.65
    izational
    0.64
    Transactional
    0.61
    Activations Density 1.068%

    No Known Activations