© 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. 2263
    Prev
    Next
    INDEX
    Explanations

    technical specifications and features of electronic components

    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
    SourceChecksum
    -0.72
     InputDecoration
    -0.61
     Paglinawan
    -0.58
     FetchType
    -0.56
     незавершена
    -0.55
     SearchView
    -0.55
    ValueStyle
    -0.54
    newtheorem
    -0.53
    Portale
    -0.53
    GROSS
    -0.52
    POSITIVE LOGITS
     Arduino
    1.01
     Raspberry
    0.87
     board
    0.80
     arduino
    0.78
     boards
    0.77
     microcontroller
    0.75
     GPIO
    0.75
    Arduino
    0.73
     PCB
    0.71
     Board
    0.69
    Activations Density 0.455%

    No Known Activations