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. 2186
    Prev
    Next
    INDEX
    Explanations

    references to various characters and elements from a fictional universe

    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
    EDEFAULT
    -0.59
     архивлан
    -0.53
    sizeCache
    -0.52
    honneur
    -0.52
     AssemblyProduct
    -0.52
     isSet
    -0.51
    IUrlHelper
    -0.50
     unknownFields
    -0.50
    ipedi
    -0.49
     invokingState
    -0.49
    POSITIVE LOGITS
    ant
    1.09
    enumi
    0.98
    ANT
    0.93
    ants
    0.88
    
    0.71
     ANT
    0.67
    anti
    0.61
    ANTS
    0.60
     Ger
    0.60
     EconPapers
    0.59
    Activations Density 2.554%

    No Known Activations