© 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-2-2B
    7. Residual Stream - 16k
    9. 11-GEMMASCOPE-RES-16K
    11. 5096
    Prev
    Next
    INDEX
    Explanations

    intensifiers and phrases that convey emphasis or exaggeration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Autowired
    -0.52
     oczywiście
    -0.50
    Ensuite
    -0.50
    specifier
    -0.48
    kegaard
    -0.47
     cạnh
    -0.46
     presumably
    -0.45
     Traditionally
    -0.45
     traditionally
    -0.45
    Parti
    -0.45
    POSITIVE LOGITS
     literally
    0.92
     Literally
    0.87
    literally
    0.86
    Literally
    0.85
     literalmente
    0.84
     truly
    0.81
    truly
    0.80
     Truly
    0.80
    Truly
    0.77
    IVEREF
    0.76
    Activations Density 0.089%

    No Known Activations