© 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-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 12215
    Prev
    Next
    INDEX
    Explanations

    references to Disney films and associated entities

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

    "in" followed by a location related to Disney

    np_acts-logits-general · gemini-2.0-flash

    locations associated with disney

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    $_['
    -0.58
    
    -0.56
     Slayer
    -0.54
    ixeira
    -0.51
     mitsubishi
    -0.50
     industriels
    -0.50
    Perth
    -0.50
     Estuary
    -0.49
    ResponseStatus
    -0.49
    IActionResult
    -0.49
    POSITIVE LOGITS
     Disney
    1.02
     Mickey
    0.91
     Walt
    0.87
    Disney
    0.85
    Mickey
    0.78
     Minnie
    0.77
    Walt
    0.75
     disney
    0.74
     Disneyland
    0.73
     parks
    0.73
    Activations Density 0.051%

    No Known Activations