© 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. 109098
    Prev
    Next
    INDEX
    Explanations

    references to individuals or people in various 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
     Person
    -1.09
    Person
    -1.09
    person
    -0.96
     PERSON
    -0.82
    PERSON
    -0.80
     person
    -0.79
     Persons
    -0.63
    Persons
    -0.58
     شخص
    -0.57
    persons
    -0.56
    POSITIVE LOGITS
    NameInMap
    0.57
    oa̍t
    0.55
    verwijspagina
    0.54
    tagHelperRunner
    0.53
    Попис
    0.49
    RTLD
    0.48
    šanu
    0.47
    StructEnd
    0.45
    RenderAtEndOf
    0.45
     okuyayım
    0.44
    Activations Density 0.005%

    No Known Activations