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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 109994
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax and structures

    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
    AnchorStyles
    -0.93
     CreateTagHelper
    -0.88
    fromnode
    -0.79
    verwijspagina
    -0.74
     ſtate
    -0.67
    titleMargin
    -0.66
     ProtoMessage
    -0.62
     ModelExpression
    -0.61
    WriteAttribute
    -0.61
    "]();
    -0.60
    POSITIVE LOGITS
     cuchara
    0.29
     broaden
    0.29
     Metern
    0.28
    EMPT
    0.28
    essoas
    0.28
     lámina
    0.28
     recuer
    0.28
     península
    0.28
     recollect
    0.27
    CLUDE
    0.27
    Activations Density 0.000%

    No Known Activations