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. 1-GEMMASCOPE-MLP-16K
    6. 8824
    Prev
    Next
    INDEX
    Explanations

    specific food-related terms and ingredients

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_1/width_16k/average_l0_105
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_mlp_out
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ties
    -0.68
     pæ
    -0.53
    toThrow
    -0.48
    addContainerGap
    -0.47
    paedia
    -0.46
    ANDED
    -0.46
    itures
    -0.45
    ̓
    -0.45
     doré
    -0.45
     BorderRadius
    -0.45
    POSITIVE LOGITS
     protoimpl
    0.98
    StructEnd
    0.85
     ModelExpression
    0.84
    ValueStyle
    0.81
    发表于
    0.80
    +#+
    0.70
     &___
    0.69
     disambiguazione
    0.68
     Audiodateien
    0.66
    getSeconds
    0.64
    Activations Density 1.073%

    No Known Activations