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. 15009
    Prev
    Next
    INDEX
    Explanations

    references to bars and their characteristics

    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
     propOrder
    -0.88
    存于互联网档案馆
    -0.68
     Sơ
    -0.67
    onViewCreated
    -0.67
    
    -0.67
    Hochspringen
    -0.67
    AccessorTable
    -0.66
     protoimpl
    -0.64
     تانيه
    -0.62
    moiselle
    -0.60
    POSITIVE LOGITS
     sl
    0.92
     Barcelona
    0.78
    sl
    0.72
    Barcelona
    0.70
     bars
    0.67
    Slim
    0.67
     SL
    0.65
     Oak
    0.65
    JsonHelper
    0.64
     slim
    0.63
    Activations Density 0.095%

    No Known Activations