© 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. 109341
    Prev
    Next
    INDEX
    Explanations

    descriptive adjectives indicating size, impact, or uniqueness

    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
     special
    -0.34
     memoized
    -0.33
    fehl
    -0.32
     специальные
    -0.31
    Géographie
    -0.31
     высокие
    -0.30
    ể
    -0.30
     conveniently
    -0.30
     my
    -0.30
     ost
    -0.29
    POSITIVE LOGITS
    <bos>
    0.88
     فريبيس
    0.75
     disambiguazione
    0.73
     Italijanski
    0.68
    OGND
    0.68
    Personendaten
    0.66
    verwijspagina
    0.65
    XmlAccessType
    0.65
    tvguidetime
    0.65
    
    0.65
    Activations Density 0.037%

    No Known Activations