Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 3259
    Prev
    Next
    INDEX
    Explanations

    references to app updates and enhancements

    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
    .”)
    -2.00
    </u>
    -1.95
    ”).
    -1.85
    ,”
    -1.74
    ”),
    -1.64
    ”)
    -1.63
    .”
    -1.56
    "));
    
    -1.47
    ),”
    -1.46
    "));
    -1.36
    POSITIVE LOGITS
    </td>
    3.01
    </th>
    1.11
    </h3>
    0.95
    </blockquote>
    0.89
    </caption>
    0.84
    </tr>
    0.81
    </s>
    0.77
    )',
    0.76
     \\
    0.76
    )';
    0.74
    Activations Density 0.155%

    No Known Activations