© 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. 15-GEMMASCOPE-RES-16K
    11. 708
    Prev
    Next
    INDEX
    Explanations

    various forms of the word "cast" and its related variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     xenia
    -1.10
     Мексичка
    -1.01
     photolibrary
    -0.99
    ViewFeatures
    -0.98
     }}"></
    -0.95
    WebVitals
    -0.94
     Whigs
    -0.94
     nakalista
    -0.93
    ergies
    -0.92
    UnknownFields
    -0.92
    POSITIVE LOGITS
     Cast
    1.68
     CAST
    1.52
     cast
    1.47
    Cast
    1.42
    cast
    1.33
     Kast
    1.32
    Kast
    1.27
    CAST
    1.24
     casts
    1.18
     casting
    1.17
    Activations Density 0.104%

    No Known Activations