© 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. 37-GEMMASCOPE-RES-16K
    6. 5279
    Prev
    Next
    INDEX
    Explanations

    terms related to travel experiences or cruise-related activities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jaros
    -0.37
     Desktop
    -0.35
     krep
    -0.35
     tráiler
    -0.35
    ngrx
    -0.35
    inerea
    -0.34
     bestanden
    -0.33
     circonstances
    -0.33
     leña
    -0.33
     bensin
    -0.33
    POSITIVE LOGITS
     cruise
    1.25
     Cruise
    1.12
     cruises
    1.05
    cruise
    1.04
    Cruise
    1.03
     cruising
    0.92
     cru
    0.91
     Cruises
    0.89
     cruisers
    0.88
     Cru
    0.81
    Activations Density 0.122%

    No Known Activations