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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K__L0-22
    6. 1096
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_22
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AsUp
    -0.82
    Искәрмәләр
    -0.81
     Sting
    -0.78
     soeur
    -0.78
     Muriel
    -0.77
     Sutherland
    -0.77
     Nier
    -0.77
     Monfieur
    -0.76
     Lyons
    -0.76
    unter
    -0.75
    POSITIVE LOGITS
    </td>
    2.11
    </blockquote>
    1.35
    </h6>
    1.10
    </h1>
    1.01
    <tr>
    0.93
    <h6>
    0.91
     \\
    0.89
    </th>
    0.88
    ')],
    0.88
    </h3>
    0.87
    Activations Density 0.004%

    No Known Activations