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 - 16k
    5. 22-GEMMASCOPE-MLP-16K
    6. 15888
    Prev
    Next
    INDEX
    Explanations

    variables and functions related to programming and data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_22/width_16k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_mlp_out
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fotografico
    -0.52
     Avez
    -0.45
     scolaires
    -0.45
    expandindo
    -0.43
     vendas
    -0.43
     listening
    -0.42
    ритори
    -0.41
    adar
    -0.40
     jugado
    -0.40
    nictví
    -0.40
    POSITIVE LOGITS
    isContained
    0.64
     oprot
    0.64
     OFDb
    0.61
    migrationBuilder
    0.60
    OwnProperty
    0.60
     وتسجيلات
    0.60
    NameInMap
    0.59
    FunctionFlags
    0.59
    RenderAtEndOf
    0.58
    ReusableCell
    0.57
    Activations Density 3.550%

    No Known Activations