© 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. 12-GEMMASCOPE-RES-16K
    6. 3753
    Prev
    Next
    INDEX
    Explanations

    references to Disney properties and related elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Rad
    -0.40
    protoimpl
    -0.39
     Bog
    -0.38
     Paglinawan
    -0.36
    Personensuche
    -0.34
    FormsModule
    -0.34
    łog
    -0.34
    appui
    -0.34
     Samp
    -0.34
     FormsModule
    -0.34
    POSITIVE LOGITS
     Disney
    1.13
    Disney
    1.09
     disney
    1.05
     Disneyland
    0.92
    disney
    0.90
    迪士尼
    0.85
    ディズニー
    0.77
     Walt
    0.73
    TypedDataSet
    0.67
    mickey
    0.63
    Activations Density 0.203%

    No Known Activations