© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 13360
    Prev
    Next
    INDEX
    Explanations

    technical terms related to frameworks and programming structures

    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
     propOrder
    -1.09
     muualla
    -0.93
     FetchType
    -0.88
     AssemblyTitle
    -0.85
    HideFlags
    -0.83
    '},
    
    -0.81
    éphane
    -0.80
    adeloupe
    -0.79
    addCriterion
    -0.79
    verwijspagina
    -0.78
    POSITIVE LOGITS
     This
    0.95
    <eos>
    0.91
    ↵↵
    0.88
      
    0.87
     The
    0.86
     ,
    0.81
     It
    0.74
       
    0.74
     These
    0.73
     You
    0.73
    Activations Density 1.008%

    No Known Activations