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-2-2B
    4. Residual Stream - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 36506
    Prev
    Next
    INDEX
    Explanations

    references to locations and spatial relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     SwiftUI
    -0.61
    ThroughAttribute
    -0.59
    AddHtmlAttribute
    -0.59
    NOPQRST
    -0.56
    PRNewswire
    -0.54
     officinalis
    -0.54
     NgModule
    -0.54
     MainAxisSize
    -0.53
    MessageOf
    -0.53
    toggler
    -0.50
    POSITIVE LOGITS
     bottom
    1.02
    bottom
    0.94
     below
    0.93
    Downs
    0.92
     descent
    0.92
     Bottom
    0.91
     downwards
    0.91
     BOTTOM
    0.90
    Bottom
    0.89
     downward
    0.89
    Activations Density 0.104%

    No Known Activations