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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 5496
    Prev
    Next
    INDEX
    Explanations

    terms related to software testing and development

    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
    存于互联网档案馆
    -0.60
     CreateTagHelper
    -0.56
    ämään
    -0.47
    jasama
    -0.47
     ferramenta
    -0.46
    lägen
    -0.45
     paille
    -0.45
     blevet
    -0.44
    usercontent
    -0.43
     mulighed
    -0.42
    POSITIVE LOGITS
    thâu
    0.79
    Билгалдахарш
    0.79
     newOwner
    0.77
    SharedDtor
    0.75
    Havolalar
    0.71
    aarrggbb
    0.71
    adaptiveStyles
    0.69
    তথ্যসূত্র
    0.66
     testers
    0.65
    forRoot
    0.65
    Activations Density 1.020%

    No Known Activations