© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. MLP Out - 131k
    9. 6-GEMMASCOPE-MLP-131K
    11. 109374
    Prev
    Next
    INDEX
    Explanations

    references to actions or events involving conflict and deceit

    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
    CloseOperation
    -0.56
    MessageTagHelper
    -0.53
     <=",
    -0.50
     kaarangay
    -0.47
    XmlRootElement
    -0.47
    OGND
    -0.45
    참고
    -0.45
    Erreferentziak
    -0.42
     CreateTagHelper
    -0.42
    Jîn
    -0.41
    POSITIVE LOGITS
     împre
    0.52
    tagez
    0.46
     ympä
    0.43
     vezes
    0.43
     sekitarnya
    0.42
     veces
    0.42
     către
    0.41
     argint
    0.41
    seamnă
    0.41
     numele
    0.40
    Activations Density 0.059%

    No Known Activations