© 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. 109286
    Prev
    Next
    INDEX
    Explanations

    references to a specific individual named Kru or Kruger in various contexts

    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
     Kru
    -2.19
    Kru
    -1.95
     kru
    -1.73
    kru
    -1.46
     Krü
    -1.10
     Kruger
    -1.09
     Кру
    -1.01
     cru
    -0.96
     Cru
    -0.95
     Kruse
    -0.95
    POSITIVE LOGITS
    PasswordEncoder
    0.58
     Caledonia
    0.50
    featureID
    0.45
    HtmlAttribute
    0.44
    jména
    0.44
     سكانية
    0.43
    inquirer
    0.42
    Gambas
    0.42
    trise
    0.41
    matchCondition
    0.40
    Activations Density 0.001%

    No Known Activations