© 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-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 1837
    Prev
    Next
    INDEX
    Explanations

    variations of the term "suit" in different contexts, particularly in relation to character or garment descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antd
    -0.42
     Knoblauch
    -0.40
    octanol
    -0.39
     poj
    -0.39
    emma
    -0.38
    спонд
    -0.38
     muchacha
    -0.38
    lexikon
    -0.37
    rogue
    -0.37
    copyFrom
    -0.36
    POSITIVE LOGITS
    suit
    0.89
    Suit
    0.87
     suit
    0.85
     Suit
    0.81
    suited
    0.72
    dic
    0.71
     suite
    0.69
    suite
    0.68
     Suite
    0.68
     suits
    0.68
    Activations Density 0.290%

    No Known Activations