© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1071
    Prev
    Next
    INDEX
    Explanations

    terms related to programming concepts, particularly regarding sessions and user interactions

    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
    StoryboardSegue
    -1.00
    IsContent
    -0.94
     myſelf
    -0.93
     doubtnut
    -0.90
     незавершена
    -0.85
     صوتيه
    -0.84
     becauſe
    -0.83
     itſelf
    -0.83
    BufferException
    -0.83
     inoxydable
    -0.83
    POSITIVE LOGITS
     data
    0.91
     information
    0.84
     value
    0.83
     info
    0.79
     mode
    0.79
     list
    0.78
     code
    0.75
     string
    0.74
     part
    0.73
     file
    0.73
    Activations Density 1.197%

    No Known Activations