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-2-2B
    4. MLP Out - 65k
    5. 0-GEMMASCOPE-MLP-65K
    6. 61057
    Prev
    Next
    INDEX
    Explanations

    inquiries about historical context and interpretations of slavery

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ↵
    -1.09
    </strong>
    -0.41
     at
    -0.40
      
    -0.39
    </h1>
    -0.39
    ش
    -0.38
    }();
    -0.38
    .
    -0.38
     por
    -0.38
    </h2>
    -0.37
    POSITIVE LOGITS
     Monfieur
    1.34
     myſelf
    1.31
     itſelf
    1.22
     himſelf
    1.21
     houſe
    1.19
     themſelves
    1.19
     raiſ
    1.18
     purpoſe
    1.18
    ^(@)
    1.17
     ſeveral
    1.17
    Activations Density 0.657%

    No Known Activations