Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Post
    5. 12-GEMMASCOPE-RES-1M
    6. 445
    Prev
    Next
    INDEX
    Explanations

    references to the Unity game engine

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_1m/average_l0_107
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    1,048,576
    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
     defaultstate
    -0.96
    хьтан
    -0.80
    Rüyada
    -0.79
     unknownFields
    -0.79
    ellido
    -0.77
     Ause
    -0.76
    ContentAlignment
    -0.76
    Geplaatst
    -0.76
     SwitchCompat
    -0.74
     AssemblyCulture
    -0.74
    POSITIVE LOGITS
     Unity
    0.82
    Unity
    0.70
    UNITY
    0.69
    unity
    0.62
     unity
    0.58
     Thurston
    0.52
    ÁL
    0.51
     puol
    0.51
    عال
    0.51
     Saltar
    0.50
    Activations Density 0.000%

    No Known Activations