© 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. 28-GEMMASCOPE-RES-16K
    6. 4677
    Prev
    Next
    INDEX
    Explanations

    references to watches and related accessories

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

    timepieces or wrist-worn items

    np_acts-logits-general · gemini-2.0-flash

    watches and wrists

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.49
    RefNanny
    -0.47
    
    -0.45
    protoimpl
    -0.44
    +#+
    -0.43
    Erstellt
    -0.42
    awtextra
    -0.40
     Truck
    -0.40
    ScopeManager
    -0.39
    évaluateur
    -0.38
    POSITIVE LOGITS
     wrist
    1.00
     watches
    0.98
     watch
    0.91
     Watches
    0.83
     smartwatch
    0.82
    wrist
    0.82
    Wrist
    0.82
    watches
    0.81
     Wrist
    0.80
     wrists
    0.79
    Activations Density 0.070%

    No Known Activations