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. 18-GEMMASCOPE-MLP-65K
    6. 94
    Prev
    Next
    INDEX
    Explanations

    instances of object-oriented programming constructs, particularly related to class and interface declarations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-mlp-65k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_18/width_65k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.18.hook_mlp_out
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SharedDtor
    -0.59
    ácara
    -0.54
    TAINMENT
    -0.52
     viewDidLoad
    -0.52
     CONTRIBUTIONS
    -0.51
    tagez
    -0.51
     utafitiHapana
    -0.50
     doInBackground
    -0.50
     ThemeData
    -0.47
     invokingState
    -0.46
    POSITIVE LOGITS
     Winaray
    0.59
    ViewImports
    0.59
     للاسماء
    0.56
    MigrationBuilder
    0.53
    AddTagHelper
    0.52
     Meksiku
    0.49
    findpost
    0.47
    __":
    0.47
     '\\;'
    0.47
    DockStyle
    0.47
    Activations Density 0.173%

    No Known Activations