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. 200
    Prev
    Next
    INDEX
    Explanations

    metrics related to vehicle performance and distance

    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
    esgue
    -0.72
     Reſ
    -0.55
    lapsingToolbar
    -0.55
     uſe
    -0.53
     ſtill
    -0.52
     CONTEST
    -0.50
     beſ
    -0.50
     himſelf
    -0.49
     GoogleFonts
    -0.49
     Majefty
    -0.48
    POSITIVE LOGITS
     виправивши
    0.93
    AndEndTag
    0.83
     ostavi
    0.71
     AssemblyCulture
    0.65
     Bioaccumulative
    0.63
    -------------</
    0.61
    ThroughAttribute
    0.60
     noDo
    0.57
    richTextPanel
    0.57
    .*")]
    0.56
    Activations Density 1.161%

    No Known Activations