© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 9281
    Prev
    Next
    INDEX
    Explanations

    HTML and scripting elements in web documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    يكب
    -0.62
     Italijanski
    -0.60
    tiérrez
    -0.59
     ainfi
    -0.58
     étoient
    -0.56
    windowFixed
    -0.54
     CALIFORNI
    -0.52
    quelles
    -0.51
     pouvoit
    -0.50
    iſter
    -0.50
    POSITIVE LOGITS
    </td>
    1.34
    </th>
    0.84
    </h2>
    0.73
    </h5>
    0.70
    </h1>
    0.66
    </h3>
    0.65
    </i>
    0.64
    </blockquote>
    0.64
     -
    0.60
     */
    0.59
    Activations Density 0.006%

    No Known Activations