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. 22-GEMMASCOPE-MLP-16K
    6. 15932
    Prev
    Next
    INDEX
    Explanations

    terms related to financial or legal definitions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __':
    
    -0.48
    تقاوى
    -0.48
     prophets
    -0.48
     rinnov
    -0.48
     Prophets
    -0.47
     Macon
    -0.47
     proprietors
    -0.45
    言い
    -0.45
    GenerationType
    -0.44
    czyny
    -0.44
    POSITIVE LOGITS
     TextAppearance
    0.65
    ノロ
    0.57
    ivoli
    0.53
     विश्वसनीयता
    0.53
    UIP
    0.52
    atisk
    0.52
    ்கள
    0.51
    Contr
    0.51
    cshtml
    0.50
    UrlResolution
    0.50
    Activations Density 0.093%

    No Known Activations