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. 61094
    Prev
    Next
    INDEX
    Explanations

    instances of the underscore character in function-like structures

    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
     rêves
    -0.69
     compréhen
    -0.68
     poursuit
    -0.66
     élevées
    -0.66
     nuages
    -0.66
    sees
    -0.64
     poursuivre
    -0.63
     để
    -0.62
     conformément
    -0.62
     Serves
    -0.59
    POSITIVE LOGITS
     depositphotos
    0.73
     Cuth
    0.71
    RefreshLayout
    0.68
     Efq
    0.65
    󠁧
    0.62
    liness
    0.61
    Personendaten
    0.61
    UFACT
    0.60
    gether
    0.60
    YOND
    0.60
    Activations Density 0.001%

    No Known Activations