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. 8858
    Prev
    Next
    INDEX
    Explanations

    references to nature and biological materials

    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
     GenerationType
    -1.48
     doubtnut
    -1.46
     ་་
    -1.43
     photolibrary
    -1.27
    GEBURTSDATUM
    -1.23
     ―――――
    -1.23
     Shakspeare
    -1.21
     ſind
    -1.20
     Pyrene
    -1.19
     betweenstory
    -1.19
    POSITIVE LOGITS
     
    0.98
    ,
    0.82
     (
    0.81
    .
    0.78
     an
    0.75
     to
    0.75
     or
    0.71
     in
    0.71
     .
    0.71
     of
    0.71
    Activations Density 22.455%

    No Known Activations