© 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. 14-GEMMASCOPE-RES-16K
    6. 7119
    Prev
    Next
    INDEX
    Explanations

    parts of code or comments that indicate the presence of a CUDA-capable GPU or device-related functions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    notices
    -0.58
    triangleq
    -0.52
     Jaffe
    -0.52
     dock
    -0.51
    Я
    -0.50
     Olsen
    -0.50
    CppMethod
    -0.50
    ”、“
    -0.49
     me
    -0.49
    пт
    -0.49
    POSITIVE LOGITS
    setVerticalGroup
    0.81
     kasarigan
    0.78
     <=",
    0.72
     שוליים
    0.72
     препратки
    0.69
    }{*}{}
    0.69
     ostavi
    0.69
    rungsseite
    0.68
     مشين
    0.68
     الحره
    0.67
    Activations Density 0.237%

    No Known Activations