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. 61031
    Prev
    Next
    INDEX
    Explanations

    HTML attributes and properties related to form elements

    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
    υχ
    -0.42
    尽く
    -0.40
    Pyx
    -0.38
     parag
    -0.38
     Vard
    -0.38
     you
    -0.37
    quait
    -0.37
     LX
    -0.36
     $\%
    -0.36
    ьажоргаш
    -0.36
    POSITIVE LOGITS
    pushFollow
    0.81
    LikeLiked
    0.81
    XmlAccessType
    0.79
    Демографія
    0.79
     CURIAM
    0.77
    Portály
    0.76
    istoitu
    0.75
     snippetHide
    0.75
    tifact
    0.72
    GEBURTSDATUM
    0.71
    Activations Density 0.049%

    No Known Activations