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. 132
    Prev
    Next
    INDEX
    Explanations

    statistics related to baseball performance

    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
    ọi
    -0.48
     pro
    -0.46
    pro
    -0.45
     tu
    -0.45
     set
    -0.44
     stri
    -0.44
     par
    -0.44
     ra
    -0.42
     ri
    -0.40
    verwijspagina
    -0.40
    POSITIVE LOGITS
    enumii
    0.80
     Мексичка
    0.78
    astify
    0.77
     pouvoit
    0.76
     Monfieur
    0.75
     Theſe
    0.74
     feroit
    0.72
    iNdEx
    0.72
     firſt
    0.71
    Tikang
    0.71
    Activations Density 0.553%

    No Known Activations