© 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. 10-GEMMASCOPE-RES-16K
    6. 15300
    Prev
    Next
    INDEX
    Explanations

    comparative phrases involving "rather than" and alternatives to typical expectations or actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     femininos
    -0.76
     IndexError
    -0.70
     Athenians
    -0.69
     Laplacian
    -0.67
     pedras
    -0.66
     թվական
    -0.65
     Legendre
    -0.65
     mußten
    -0.65
     Sapp
    -0.64
     Hebron
    -0.64
    POSITIVE LOGITS
     Instead
    1.01
    Instead
    1.01
     instead
    0.97
     Rather
    0.84
     rather
    0.81
    Rather
    0.81
     zamiast
    0.75
     statt
    0.74
     Statt
    0.73
     बजाय
    0.73
    Activations Density 0.081%

    No Known Activations