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-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 109832
    Prev
    Next
    INDEX
    Explanations

    occurrences of possessive pronouns indicating ownership or association

    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
     
    -0.41
    getStatusCode
    -0.39
     Gottfried
    -0.36
     mas
    -0.35
     CR
    -0.35
     schon
    -0.35
     mod
    -0.34
     —
    -0.34
    fsch
    -0.34
     autom
    -0.33
    POSITIVE LOGITS
    цездатний
    0.66
     beginnetje
    0.64
     réaliste
    0.58
    Personensuche
    0.57
    
    0.57
    хьтан
    0.56
     ModelExpression
    0.55
    ロウィン
    0.55
     poveznice
    0.54
    MessageTagHelper
    0.53
    Activations Density 0.011%

    No Known Activations