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. 0-GEMMASCOPE-MLP-16K
    6. 2
    Prev
    Next
    INDEX
    Explanations

    instances of the word "deep" or its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the concept of depth in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-mlp-16k
    Configuration
    google/gemma-scope-2b-pt-mlp/layer_0/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_mlp_out
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     deep
    -1.59
    deep
    -1.11
    Deep
    -0.91
     Deep
    -0.88
    MLLoader
    -0.84
    HtmlAttribute
    -0.77
     DEEP
    -0.75
    BufferException
    -0.73
    sidemargin
    -0.69
    msgSender
    -0.68
    POSITIVE LOGITS
     récentes
    0.63
    湎
    0.59
    łop
    0.59
     <<<<<<<<<<<<<<
    0.58
     allmän
    0.58
     culturelles
    0.56
     ouvertes
    0.56
    anyika
    0.55
     docteur
    0.53
     verdade
    0.52
    Activations Density 0.094%

    No Known Activations