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. 114517
    Prev
    Next
    INDEX
    Explanations

    references to the UK

    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
    hazel
    -0.52
    abstractmethod
    -0.52
    featureID
    -0.52
    antin
    -0.49
     BoxFit
    -0.49
    spr
    -0.48
    FieldDescriptor
    -0.48
    ransition
    -0.47
     tartalomajánló
    -0.47
    AddHtmlAttribute
    -0.47
    POSITIVE LOGITS
     UK
    0.84
    UK
    0.79
     Unido
    0.68
     Uk
    0.66
    Uk
    0.66
     Económica
    0.61
     británica
    0.61
     Britain
    0.60
    Britain
    0.59
     uk
    0.58
    Activations Density 0.008%

    No Known Activations