© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 798
    Prev
    Next
    INDEX
    Explanations

    phrases related to programming, digital communication, and multimedia 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
    gebnissen
    -0.49
     özellik
    -0.48
     Tagen
    -0.47
     Jahren
    -0.47
     sposo
    -0.47
     ошибок
    -0.45
    trägen
    -0.45
     Punkten
    -0.44
     файлов
    -0.43
     Bildern
    -0.42
    POSITIVE LOGITS
     linkovi
    0.56
     cottura
    0.54
     AssemblyCompany
    0.51
     betweenstory
    0.51
    niſſe
    0.51
    сылкі
    0.50
    ValueStyle
    0.50
    Obrázky
    0.49
    vece
    0.49
     CreateTagHelper
    0.48
    Activations Density 0.071%

    No Known Activations