© 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-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 9387
    Prev
    Next
    INDEX
    Explanations

    the presence of the word "two" and its variations in numeric and textual forms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.41
    InputBorder
    -0.40
    Datuak
    -0.40
    ContentAsync
    -0.38
     Grüsse
    -0.37
    enskap
    -0.37
     Estimation
    -0.35
    withIdentifier
    -0.35
     Stabilization
    -0.35
    muerzo
    -0.35
    POSITIVE LOGITS
     two
    2.20
     deux
    1.93
     zwei
    1.84
    two
    1.81
    Two
    1.73
     three
    1.70
     TWO
    1.68
     duas
    1.62
     Two
    1.61
     två
    1.61
    Activations Density 0.413%

    No Known Activations