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. 19-GEMMASCOPE-RES-16K
    6. 11212
    Prev
    Next
    INDEX
    Explanations

    references to programming functions and object-oriented structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.93
      
    -0.92
     ,
    -0.72
     "
    -0.60
       
    -0.58
     my
    -0.58
     .
    -0.57
     I
    -0.56
     y
    -0.54
     K
    -0.54
    POSITIVE LOGITS
     AspNetCore
    1.33
    DockStyle
    1.21
    
    1.17
     auffi
    1.12
     Majefty
    1.11
     Efq
    1.10
     MainAxisSize
    1.09
     ―――――
    1.08
     ་་
    1.08
     iſt
    1.07
    Activations Density 1.779%

    No Known Activations