© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6782
    Prev
    Next
    INDEX
    Explanations

    references to rings symbolizing love or commitment, particularly in the context of weddings and anniversaries

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    jewelry and rings

    np_acts-logits-general · gemini-2.0-flash

    jewelry

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tarp
    -0.47
     pitching
    -0.42
     pitch
    -0.41
     Pitch
    -0.41
     pitched
    -0.39
    dataclass
    -0.39
    pitched
    -0.38
     telt
    -0.37
     Spare
    -0.37
     poster
    -0.37
    POSITIVE LOGITS
     Jewelry
    0.85
     jewelry
    0.84
     jewellery
    0.79
     joyería
    0.79
    Jewelry
    0.78
    jewelry
    0.77
     Jewellery
    0.68
    lgari
    0.64
     bague
    0.60
     gioielli
    0.58
    Activations Density 0.058%

    No Known Activations