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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 110129
    Prev
    Next
    INDEX
    Explanations

    references to hairstyles and hair-related styles

    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
     hairstyle
    -1.50
     hairstyles
    -1.42
     Hairst
    -1.01
     haircuts
    -1.01
     haircut
    -0.95
     peinados
    -0.83
     hairst
    -0.75
     coiffure
    -0.73
     hairdresser
    -0.68
     peinado
    -0.68
    POSITIVE LOGITS
     onOptions
    0.45
    findpost
    0.43
    fjspx
    0.42
    propTypes
    0.39
     délib
    0.37
    äsident
    0.36
    varargin
    0.35
    TypedDataSet
    0.35
    PerformLayout
    0.35
    DeleteMapping
    0.34
    Activations Density 0.000%

    No Known Activations