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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 37-GEMMASCOPE-RES-16K
    6. 4173
    Prev
    Next
    INDEX
    Explanations

    technical terms related to quantum field theory and perturbation series

    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
    keyColumn
    -0.40
    êté
    -0.36
     fiches
    -0.34
    albero
    -0.34
    Mode
    -0.34
     missionary
    -0.34
     modalità
    -0.33
     mode
    -0.33
    زر
    -0.32
     Mode
    -0.32
    POSITIVE LOGITS
     estekak
    0.60
     Quark
    0.58
    новништво
    0.57
    SharedDtor
    0.56
     kasarigan
    0.56
     quark
    0.55
    contentLoaded
    0.54
     Parton
    0.53
    الحياه
    0.52
     gluon
    0.52
    Activations Density 0.500%

    No Known Activations