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. 61083
    Prev
    Next
    INDEX
    Explanations

    instances of funding-related terminology

    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
     Cæsar
    -0.90
     Diſ
    -0.82
     Houſe
    -0.81
     Perſ
    -0.81
    Back
    -0.81
     Conſ
    -0.80
     Inſ
    -0.78
    Up
    -0.75
     Monfieur
    -0.73
     Theſe
    -0.71
    POSITIVE LOGITS
    ########.
    0.89
    SharedDtor
    0.88
    IsMutable
    0.88
     مرئيه
    0.87
    InputTagHelper
    0.86
    +#+#
    0.86
    underwater
    0.86
    usermodel
    0.85
    Autoritní
    0.84
    ItemBackground
    0.84
    Activations Density 0.009%

    No Known Activations