© 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. 3-GEMMASCOPE-RES-16K
    6. 9554
    Prev
    Next
    INDEX
    Explanations

    elements related to document structure in LaTeX code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     GetComponent
    -0.51
     стаття
    -0.48
    ois
    -0.46
    Xtra
    -0.46
    lls
    -0.46
    րջ
    -0.45
    webkit
    -0.45
    </em>
    -0.45
    ICTS
    -0.45
    itev
    -0.45
    POSITIVE LOGITS
    GraphicsUnit
    1.62
    documentclass
    1.58
    tagHelperRunner
    1.27
     Bluetooth
    1.08
     ComVisible
    1.05
     GenerationType
    1.03
     AssemblyVersion
    1.01
    URLException
    0.99
    Bluetooth
    0.98
    styleUrls
    0.97
    Activations Density 0.074%

    No Known Activations