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. 1-GEMMASCOPE-RES-16K
    6. 13654
    Prev
    Next
    INDEX
    Explanations

    terms related to programming and software development, especially involving specific functions or methods in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षक
    -0.54
     gili
    -0.54
     big
    -0.52
    تع
    -0.50
    師
    -0.49
     relying
    -0.49
    indon
    -0.49
    *~*~
    -0.49
     AppBundle
    -0.48
     reliance
    -0.48
    POSITIVE LOGITS
    __':
    
    0.78
    ReusableCell
    0.73
    SBATCH
    0.71
    tableFuture
    0.69
     Chwiliwch
    0.68
     BorderRadius
    0.67
     Oath
    0.66
    AddHtmlAttribute
    0.66
    breath
    0.65
     nobler
    0.64
    Activations Density 2.384%

    No Known Activations