© 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. 11226
    Prev
    Next
    INDEX
    Explanations

    references to terms and their definitions or classifications within a context

    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
    door
    -0.55
     QLabel
    -0.54
    getchar
    -0.53
     nif
    -0.51
     Waray
    -0.50
     IDL
    -0.49
    '][$
    -0.49
    ος
    -0.48
     pertin
    -0.48
    Xna
    -0.47
    POSITIVE LOGITS
     发表于
    0.66
    windowFixed
    0.64
     ostavi
    0.64
    BindingResult
    0.58
    sizeCache
    0.57
    tahui
    0.55
     suspensão
    0.54
    CppCodeGen
    0.53
     hjel
    0.52
     list
    0.52
    Activations Density 0.655%

    No Known Activations