© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 110746
    Prev
    Next
    INDEX
    Explanations

    type parameters and template syntax in programming

    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
     Supreme
    -0.33
     Gier
    -0.32
     Federico
    -0.32
     proposed
    -0.32
     professional
    -0.30
     Bischof
    -0.30
    mathbb
    -0.30
     Terr
    -0.29
     Schub
    -0.29
     vong
    -0.29
    POSITIVE LOGITS
    fjspx
    0.69
    LookAnd
    0.67
     nahilalakip
    0.65
    Datuak
    0.63
    jsii
    0.63
    InitVars
    0.57
    DrawerToggle
    0.57
    InputBorder
    0.56
     resourceCulture
    0.56
    InputTagHelper
    0.56
    Activations Density 0.279%

    No Known Activations