© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 108612
    Prev
    Next
    INDEX
    Explanations

    mentions of the game "Candy Crush."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     crush
    -1.65
     Crush
    -1.31
    Crush
    -1.28
    crush
    -1.27
     crushes
    -1.12
     crushing
    -0.91
     crusher
    -0.80
     crushed
    -0.75
    뀜
    -0.55
     Crus
    -0.52
    POSITIVE LOGITS
    UrlResolution
    0.47
    weightedMode
    0.43
     myſelf
    0.41
     ffilmiau
    0.37
     juſt
    0.37
    出版年
    0.37
     ſta
    0.36
    ErrUnexpectedEOF
    0.36
    ruptedException
    0.35
    WriteBarrier
    0.35
    Activations Density 0.000%

    No Known Activations