© 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. 0-GEMMASCOPE-RES-16K
    11. 8701
    Prev
    Next
    INDEX
    Explanations

    expressions of surprise and strong reactions

    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
    AnchorTagHelper
    -0.50
     enfans
    -0.48
     uLocal
    -0.47
     masculinos
    -0.45
    Cyfeiriadau
    -0.45
    ſelves
    -0.45
    EndGlobalSection
    -0.44
     betweenstory
    -0.44
     condam
    -0.43
     AssemblyCulture
    -0.42
    POSITIVE LOGITS
     amazed
    1.77
     shocked
    1.66
     surprised
    1.64
     astonished
    1.62
     thrilled
    1.58
     delighted
    1.50
     horrified
    1.46
     impressed
    1.44
     stunned
    1.42
     startled
    1.42
    Activations Density 0.189%

    No Known Activations