© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 108525
    Prev
    Next
    INDEX
    Explanations

    expressions related to personal preferences and tastes

    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
     liking
    -1.65
     menyukai
    -0.67
     preferring
    -0.64
    webElementGuid
    -0.63
     gustó
    -0.63
    Likes
    -0.62
     gillar
    -0.61
     loving
    -0.60
    喜欢
    -0.60
    喜好
    -0.59
    POSITIVE LOGITS
     zar
    0.37
     Y
    0.36
    ErrUnexpectedEOF
    0.35
     اتحاد
    0.35
    टन
    0.33
    ensatz
    0.32
    erville
    0.32
    lad
    0.31
     B
    0.31
     vie
    0.31
    Activations Density 0.001%

    No Known Activations