Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 73762
    Prev
    Next
    INDEX
    Explanations

    references to Prime Ministers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.52
    dataclass
    -0.51
     CreateTagHelper
    -0.48
     calendriers
    -0.48
     BoxFit
    -0.46
     AttributeSet
    -0.46
     BoxDecoration
    -0.45
    Fluffy
    -0.44
    licted
    -0.44
     Filed
    -0.44
    POSITIVE LOGITS
     AssemblyCompany
    0.56
     PM
    0.52
     Minister
    0.51
     الوزراء
    0.50
    lusconi
    0.49
    WindowConstants
    0.49
    HomeController
    0.48
    minister
    0.47
     government
    0.47
     Premi
    0.46
    Activations Density 0.006%

    No Known Activations