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. 73436
    Prev
    Next
    INDEX
    Explanations

    specific locations and venues mentioned in the text

    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
     StringVar
    -0.50
     FormsModule
    -0.44
     Familienname
    -0.43
     István
    -0.42
    componentWill
    -0.41
    horizontalLayout
    -0.41
     Chowdhury
    -0.40
     pymongo
    -0.40
     Prussian
    -0.40
     Dabei
    -0.39
    POSITIVE LOGITS
     locations
    0.67
     location
    0.65
     Location
    0.62
     places
    0.61
     위치
    0.57
     Locations
    0.56
     getLocation
    0.55
    بوابة
    0.55
     South
    0.54
     North
    0.54
    Activations Density 0.023%

    No Known Activations