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. 2449
    Prev
    Next
    INDEX
    Explanations

    technical terms and processes related to programming and data manipulation

    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
     elettrica
    -0.99
     chinoise
    -0.94
     espagnole
    -0.94
     asiatique
    -0.93
     contemporaine
    -0.92
     neuve
    -0.90
     humaines
    -0.89
     asiática
    -0.88
     umana
    -0.86
     africaine
    -0.86
    POSITIVE LOGITS
     de
    0.73
    %")
    0.64
    ทาง
    0.63
    "]:
    0.62
    }}],
    0.62
     '\\;'
    0.62
    ']))
    
    0.61
    
    0.61
    Географи
    0.59
    )|\
    0.58
    Activations Density 0.088%

    No Known Activations