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 - 16k
    5. 6-GEMMASCOPE-MLP-16K
    6. 195
    Prev
    Next
    INDEX
    Explanations

    references to familial relationships, particularly related to sons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     retired
    -0.46
    entuh
    -0.46
    पुर
    -0.46
    ashian
    -0.40
    
    -0.40
    Bibliografia
    -0.40
    ดุ
    -0.40
    dropna
    -0.39
     sentimos
    -0.39
    vyš
    -0.39
    POSITIVE LOGITS
    ChildIndex
    0.89
     child
    0.89
    child
    0.87
     childs
    0.86
     children
    0.84
     kid
    0.82
     kids
    0.81
     CHILD
    0.81
     youngest
    0.80
    AndroidJUnit
    0.80
    Activations Density 0.309%

    No Known Activations