© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. MLP Out - 131k
    5. 6-GEMMASCOPE-MLP-131K
    6. 108697
    Prev
    Next
    INDEX
    Explanations

    mentions of genes and their regulatory patterns in biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-mlp/layer_6/width_131k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     يتيمه
    -0.65
    OGND
    -0.63
    참고
    -0.56
    expandindo
    -0.55
     Wikimedijinoj
    -0.54
    aarrggbb
    -0.54
    adpleegd
    -0.53
     мәкалә
    -0.52
    Diweddarwch
    -0.50
    Kariera
    -0.47
    POSITIVE LOGITS
    TableField
    0.36
    "]).
    0.35
     Feier
    0.35
    gridy
    0.34
    layoutControl
    0.34
    miyorum
    0.33
    setCellStyle
    0.32
    дьми
    0.32
    ModelForm
    0.31
    createCell
    0.31
    Activations Density 0.406%

    No Known Activations