© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7770
    Prev
    Next
    INDEX
    Explanations

    references to various fields of physics, including specific terminology and journal titles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CppMethod
    -0.57
     Италијани
    -0.54
    存于互联网档案馆
    -0.47
    setupUi
    -0.43
     HasFactory
    -0.42
     famí
    -0.41
    fromnode
    -0.41
    shoe
    -0.41
     ThemeData
    -0.40
     Roskov
    -0.40
    POSITIVE LOGITS
    Phys
    1.27
     PHYS
    1.16
     Phys
    1.08
    PHYS
    1.05
    phys
    1.05
     phys
    1.02
     physically
    0.92
     Physically
    0.92
     physical
    0.90
    Physical
    0.90
    Activations Density 0.774%

    No Known Activations