© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 4893
    Prev
    Next
    INDEX
    Explanations

    JavaScript functions that manipulate the Document Object Model (DOM)

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    enseits
    -0.74
     SwitchCompat
    -0.71
     اكتوبر
    -0.65
    dags
    -0.64
     transfieras
    -0.64
    Zacks
    -0.64
     Imagination
    -0.63
     setType
    -0.62
     IMPLIED
    -0.62
    mybatisplus
    -0.62
    POSITIVE LOGITS
    getElementById
    2.25
    querySelector
    1.50
    querySelectorAll
    0.95
    getElementsBy
    0.91
    createElement
    0.81
    prepareStatement
    0.75
    IBOutlet
    0.71
    labelledby
    0.70
    documentElement
    0.69
    #+#
    0.65
    Activations Density 0.019%

    No Known Activations