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. 6-GEMMASCOPE-MLP-16K
    6. 36
    Prev
    Next
    INDEX
    Explanations

    instances of error messages and invalid URLs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 6-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_6/width_16k/average_l0_133
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.6.hook_mlp_out
    Hook Layer
    6
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    matchCondition
    -0.71
    contentLoaded
    -0.69
     CreateTagHelper
    -0.65
    Билгалдахарш
    -0.63
     otomatig
    -0.60
    RepeatedField
    -0.58
     Reverso
    -0.57
     PropertyChanged
    -0.56
     &___
    -0.56
    awaiter
    -0.55
    POSITIVE LOGITS
    SequentialGroup
    0.52
     initComponents
    0.50
    polate
    0.49
    umán
    0.48
    Hochspringen
    0.48
    UMB
    0.47
     pince
    0.47
    ternut
    0.46
    mase
    0.45
    ITECT
    0.45
    Activations Density 0.415%

    No Known Activations