© 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. 25-GEMMASCOPE-RES-16K
    11. 1662
    Prev
    Next
    INDEX
    Explanations

    financial or mathematical symbols and notation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.99
    </strong>
    -0.80
    </u>
    -0.78
    </i>
    -0.59
    ,”
    -0.53
    </h2>
    -0.52
    }*/
    -0.52
    ”,
    -0.51
     }
    -0.46
    ”
    -0.46
    POSITIVE LOGITS
    <td>
    1.99
    <th>
    1.17
    </tr>
    0.88
    <tr>
    0.82
    AccessorTable
    0.73
    XmlAccessorType
    0.72
    td
    0.72
     Roskov
    0.71
     Winaray
    0.69
    esgue
    0.69
    Activations Density 0.007%

    No Known Activations