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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15117
    Prev
    Next
    INDEX
    Explanations

    HTML elements and their attributes related to button configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Искәрмәләр
    -0.99
    __':
    
    -0.97
    ConstraintMaker
    -0.96
     Efq
    -0.88
    ⓘ
    -0.88
    хьтан
    -0.87
    DockStyle
    -0.85
    imanapun
    -0.84
    AsUp
    -0.83
    ագրություններ
    -0.82
    POSITIVE LOGITS
      
    0.74
       
    0.55
     
    0.50
    id
    0.48
     id
    0.45
     ,
    0.42
    LookAnd
    0.41
        
    0.41
     P
    0.41
         
    0.40
    Activations Density 0.104%

    No Known Activations