© 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. 11796
    Prev
    Next
    INDEX
    Explanations

    LaTeX document structure elements and commands

    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
    Datuak
    -0.80
     مشين
    -0.76
    HasForeignKey
    -0.74
    queryInterface
    -0.73
    writeFieldEnd
    -0.73
    RectangleBorder
    -0.70
     BorderRadius
    -0.68
    ثيق
    -0.68
    хьтан
    -0.67
    MethodManager
    -0.66
    POSITIVE LOGITS
    documentclass
    0.82
    Rig
    0.54
    UserScript
    0.54
     fart
    0.51
    assword
    0.50
    odzi
    0.49
    cl
    0.46
     farewell
    0.45
    Setup
    0.45
     tels
    0.45
    Activations Density 0.098%

    No Known Activations