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. 8732
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and references to functions and variables

    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
    ']
    
    -0.56
     Rä
    -0.54
    "]
    
    -0.53
    qxd
    -0.53
     Tab
    -0.51
    breviation
    -0.51
     date
    -0.50
    الإنجليزية
    -0.50
     }}=
    -0.50
     fidanz
    -0.49
    POSITIVE LOGITS
     >=",
    0.72
    Composable
    0.70
    parsedMessage
    0.70
     оригіналу
    0.69
    Espèce
    0.67
     Drapeau
    0.67
    WithIOException
    0.62
     lenker
    0.61
    JspWriter
    0.61
     snippetHide
    0.58
    Activations Density 0.182%

    No Known Activations