© 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-2-2B
    7. Residual Stream - 16k
    9. 10-GEMMASCOPE-RES-16K
    11. 3522
    Prev
    Next
    INDEX
    Explanations

    tokens that indicate the beginning of a new section or significant entry point in a document

    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
     يتيمه
    -0.95
    WebMethod
    -0.93
     otomatig
    -0.92
    SharedDtor
    -0.91
    PMailer
    -0.88
    دانشنامهٔ
    -0.87
    +#+
    -0.86
     layui
    -0.84
     Hendrick
    -0.83
    Erick
    -0.81
    POSITIVE LOGITS
    <h3>
    1.05
    \
    1.04
    <h2>
    1.00
    ↵↵
    0.94
    </tr>
    0.83
    <h4>
    0.83
    </table>
    0.79
    <h1>
    0.76
     \
    0.73
    <tbody>
    0.72
    Activations Density 0.012%

    No Known Activations