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. 43332
    Prev
    Next
    INDEX
    Explanations

    references to partnerships or collaborations in business contexts

    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
     Theſe
    -1.05
     myſelf
    -0.96
    WebVitals
    -0.95
    ValueStyle
    -0.92
     Houſe
    -0.91
     resourceCulture
    -0.90
    AddTagHelper
    -0.90
     Shakspeare
    -0.89
     Efq
    -0.87
     Monfieur
    -0.87
    POSITIVE LOGITS
     –
    0.53
     e
    0.50
     
    0.49
      
    0.49
     #
    0.49
    ,
    0.48
     (
    0.45
     challenging
    0.45
     
    0.44
     V
    0.43
    Activations Density 0.103%

    No Known Activations