© 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-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13008
    Prev
    Next
    INDEX
    Explanations

    intensifying adverbs that express totality or agreement

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     EconPapers
    -0.65
     argc
    -0.59
     desorption
    -0.57
    知る
    -0.56
     trouvez
    -0.56
    formik
    -0.55
     denn
    -0.53
    ijão
    -0.53
    umball
    -0.53
     yoksa
    -0.53
    POSITIVE LOGITS
     completely
    4.18
     Completely
    3.77
    completely
    3.72
     totally
    3.57
    Completely
    3.55
     entirely
    3.49
    totally
    3.04
     Totally
    3.03
    Totally
    2.91
     complètement
    2.88
    Activations Density 0.087%

    No Known Activations