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. 61111
    Prev
    Next
    INDEX
    Explanations

    mentions of specific model identifiers related to vehicles

    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
    й
    -0.62
    teen
    -0.59
    structors
    -0.56
     pij
    -0.54
    icians
    -0.53
    teenth
    -0.53
    osp
    -0.53
     pinulongan
    -0.51
    ressão
    -0.50
    vierte
    -0.48
    POSITIVE LOGITS
     disambiguazione
    0.99
    oredCriteria
    0.96
    sizeCache
    0.93
    oubted
    0.78
     faſt
    0.77
    unconfirmed
    0.76
    webElementXpaths
    0.74
     juſ
    0.73
    Geplaatst
    0.73
     IDisposable
    0.73
    Activations Density 0.013%

    No Known Activations