© 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. 0-GEMMASCOPE-RES-16K
    11. 14968
    Prev
    Next
    INDEX
    Explanations

    references to the word "Shi" and variations of the word "Stone" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WriteAttribute
    -0.52
    Ditto
    -0.50
    Vidite
    -0.49
     Ditto
    -0.49
    centerline
    -0.48
    ecture
    -0.47
     Egal
    -0.47
    Izvori
    -0.47
    tame
    -0.45
    뚠
    -0.45
    POSITIVE LOGITS
     Stone
    0.57
     Shi
    0.55
    WindowConstants
    0.52
     se
    0.50
    Stone
    0.50
    Shi
    0.45
    IndentedString
    0.44
     Lieutenant
    0.42
     culture
    0.41
     STONE
    0.40
    Activations Density 0.224%

    No Known Activations