© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 1315
    Prev
    Next
    INDEX
    Explanations

    symbols and mathematical expressions related to formal equations and inequalities

    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
    SourceChecksum
    -0.59
    principalColumn
    -0.56
    tagHelperRunner
    -0.54
    ➟
    -0.54
    Enc
    -0.52
     Exactos
    -0.51
    pexpr
    -0.50
    Eme
    -0.50
    Irak
    -0.49
    Edi
    -0.49
    POSITIVE LOGITS
    appui
    0.70
    assemblée
    0.66
    amitié
    0.66
    épaisseur
    0.65
    aménagement
    0.65
    atteindre
    0.62
    accompagnement
    0.58
    arrêter
    0.58
    Assemblée
    0.56
    amélioration
    0.56
    Activations Density 1.377%

    No Known Activations