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. 2-GEMMASCOPE-RES-16K
    6. 6226
    Prev
    Next
    INDEX
    Explanations

    technical terms related to music production and software frameworks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     OFDb
    -0.76
     beginnetje
    -0.70
    PhysRevD
    -0.70
    '));
    
    -0.67
    '))
    
    -0.66
    SBATCH
    -0.66
     समीक्षाओं
    -0.64
    GEBURTSDATUM
    -0.64
    ganu
    -0.64
     jScrollPane
    -0.64
    POSITIVE LOGITS
    TagHelpers
    0.89
     EdgeInsets
    0.71
    pyx
    0.57
    Alignment
    0.57
    dart
    0.55
    EClass
    0.46
    WEBPACK
    0.45
    createElement
    0.43
    Rüyada
    0.42
     gereken
    0.41
    Activations Density 1.985%

    No Known Activations