© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 908
    Prev
    Next
    INDEX
    Explanations

    keywords and methods related to managing application state in Java-based applications

    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
     odkazy
    -0.45
    onday
    -0.44
    それと
    -0.43
    près
    -0.42
     Shall
    -0.41
    Shall
    -0.41
     nhập
    -0.40
     iden
    -0.39
    Ự
    -0.39
     Príncipe
    -0.38
    POSITIVE LOGITS
    :✨
    1.10
    HtmlAttribute
    0.91
    InstanceState
    0.81
    
    0.80
    发表于
    0.78
    thâu
    0.75
    ard
    0.73
    ec
    0.71
    EC
    0.70
     protoimpl
    0.69
    Activations Density 2.237%

    No Known Activations