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. 24-GEMMASCOPE-RES-16K
    6. 2366
    Prev
    Next
    INDEX
    Explanations

    specific formatting elements in HTML or XML-like structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML tags and attributes

    np_acts-logits-general · gemini-2.0-flash

    html elements and attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     насељу
    -0.66
    niająca
    -0.65
    sizeCache
    -0.60
    astéro
    -0.59
     noDo
    -0.57
    [])
    
    -0.56
     rhestr
    -0.55
    reibung
    -0.54
     EnglishChoose
    -0.54
     ſta
    -0.53
    POSITIVE LOGITS
    </
    1.49
    </td>
    0.97
    <
    0.97
    </tr>
    0.89
    </caption>
    0.84
    <!--
    0.82
    </th>
    0.79
    </thead>
    0.78
    </h6>
    0.78
    </table>
    0.76
    Activations Density 0.044%

    No Known Activations