Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 109607
    Prev
    Next
    INDEX
    Explanations

    financial terms and related numerical values

    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
     ق
    -0.34
    ใช่
    -0.34
     fraction
    -0.33
     besides
    -0.32
     aside
    -0.32
     Fraction
    -0.31
     franchises
    -0.31
    fraction
    -0.29
    廉
    -0.29
     во
    -0.28
    POSITIVE LOGITS
     autorytatywna
    0.75
     disambiguazione
    0.73
    تقاوى
    0.70
    SourceChecksum
    0.69
    queryInterface
    0.67
    JspWriter
    0.63
    tagHelperRunner
    0.63
     snippetHide
    0.61
    脚注の使い方
    0.61
    Geplaatst
    0.60
    Activations Density 0.045%

    No Known Activations