© 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. 110272
    Prev
    Next
    INDEX
    Explanations

    instances of the word "no" and its variants in different languages

    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
     conten
    -0.41
     prefeitura
    -0.40
    емость
    -0.40
    AsStream
    -0.39
    unhofer
    -0.39
     îna
    -0.38
    iibo
    -0.37
     trebui
    -0.36
     ſte
    -0.36
    :✨
    -0.36
    POSITIVE LOGITS
    Rüyada
    0.55
    ValueStyle
    0.53
    ंदीखरीदारी
    0.46
    aarrggbb
    0.44
    typeorm
    0.43
    oredCriteria
    0.43
     surla
    0.43
    omitempty
    0.43
    ⓧ
    0.42
     AppCompatTheme
    0.42
    Activations Density 0.004%

    No Known Activations