© 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. 7933
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "trick" 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
     pleaſure
    -0.90
     houſe
    -0.87
     Houſe
    -0.86
     ſta
    -0.85
     ſte
    -0.82
     itſelf
    -0.79
     myſelf
    -0.78
     raiſ
    -0.77
     ſever
    -0.69
    ſelf
    -0.69
    POSITIVE LOGITS
     multiply
    0.49
     Multiply
    0.47
    multiply
    0.45
     trick
    0.43
    trick
    0.42
     kiin
    0.40
    Multiply
    0.39
     excelencia
    0.38
     multiplied
    0.38
     rokok
    0.38
    Activations Density 0.225%

    No Known Activations