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. 109759
    Prev
    Next
    INDEX
    Explanations

    instances of legal or financial terms related to contracts and agreements

    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
     nhận
    -0.35
     recevoir
    -0.33
     Receive
    -0.33
     CLAIMS
    -0.32
     Claim
    -0.32
    Receive
    -0.32
     claimed
    -0.31
     récla
    -0.31
     RECEIVE
    -0.30
     SAMPLES
    -0.29
    POSITIVE LOGITS
     HasFactory
    0.77
    ChildScrollView
    0.76
     GenerationType
    0.73
     Wikimedijinoj
    0.69
    CloseOperation
    0.67
     المعيارى
    0.66
    хьтан
    0.61
    المناصب
    0.60
     JpaRepository
    0.60
     BoxFit
    0.60
    Activations Density 0.061%

    No Known Activations