© 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. 0-GEMMASCOPE-RES-16K
    11. 8242
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to glue and bonding mechanisms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    displaymath
    -0.40
    
    -0.40
     utafitiHapana
    -0.37
     inteiro
    -0.36
     Ró
    -0.36
     Tade
    -0.35
    ArrowToggle
    -0.35
     Polak
    -0.35
     Kwon
    -0.34
    KommentareTeilen
    -0.34
    POSITIVE LOGITS
     Glue
    0.74
     BoxFit
    0.72
     glue
    0.70
     sticky
    0.64
     AssemblyTitle
    0.64
     Sticky
    0.60
    glue
    0.58
    Glue
    0.57
     Ring
    0.54
    CppMethod
    0.54
    Activations Density 1.596%

    No Known Activations