© 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. 109904
    Prev
    Next
    INDEX
    Explanations

    phrases indicating processes or relationships involving responsibility and action within a defined framework

    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
    spesies
    -0.39
    bmod
    -0.39
    cedido
    -0.38
    scriptcase
    -0.36
     ✭✭
    -0.36
     OMITBAD
    -0.36
    Ắ
    -0.35
    Royaume
    -0.35
     revenus
    -0.35
     iesp
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.49
     strictly
    0.46
    밌
    0.44
    jsxFileName
    0.43
    AnimationsModule
    0.42
    ISupport
    0.42
    InjectAttribute
    0.42
     snippetHide
    0.41
    LLocation
    0.40
     تضيفلها
    0.40
    Activations Density 0.605%

    No Known Activations