© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1033
    Prev
    Next
    INDEX
    Explanations

    instances of the word "demonstrate" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    URLException
    -1.09
    InjectMocks
    -0.80
    Guido
    -0.78
     BitmapFactory
    -0.76
    lgari
    -0.75
     كومونز
    -0.75
     TextAppearance
    -0.74
     Jolie
    -0.74
    NewUrlParser
    -0.74
     consultato
    -0.74
    POSITIVE LOGITS
     demonstrated
    1.15
     demonstrate
    1.02
     demonstrating
    0.97
     demonstrates
    0.95
     demonstration
    0.92
     demonstrations
    0.91
     Demonstrate
    0.84
     Demonstration
    0.79
     Demonstr
    0.79
    Demonstration
    0.75
    Activations Density 0.125%

    No Known Activations