© 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. 1-GEMMASCOPE-RES-16K
    6. 15408
    Prev
    Next
    INDEX
    Explanations

    references to web resources, particularly related to Bootstrap and other libraries

    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
     betweenstory
    -0.67
    سوب
    -0.57
    Filmographie
    -0.54
    ifrance
    -0.54
     дописавши
    -0.53
    abatic
    -0.53
    PreferredItem
    -0.52
    ├──
    -0.51
    Enllaces
    -0.50
    المناصب
    -0.50
    POSITIVE LOGITS
     Scatter
    0.76
    AxisAlignment
    0.73
     scattered
    0.68
    scatter
    0.67
    PMailer
    0.66
    Scatter
    0.64
    gan
    0.62
    kan
    0.62
    ip
    0.60
    KAN
    0.58
    Activations Density 2.194%

    No Known Activations