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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 14465
    Prev
    Next
    INDEX
    Explanations

    HTML or XML tags and their attributes

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

    HTML table-related tokens

    np_acts-logits-general · gemini-2.0-flash

    html closing tags

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zehn
    -0.59
    reducers
    -0.57
    AsUp
    -0.56
     EClass
    -0.56
    putAll
    -0.56
    PYX
    -0.54
     @{
    -0.53
    ylase
    -0.52
    unknownFields
    -0.52
    ('./
    -0.52
    POSITIVE LOGITS
    </td>
    1.05
    </th>
    0.82
    <tr>
    0.76
    </h6>
    0.74
    endregion
    0.69
    <tbody>
    0.69
    ]),
    
    0.66
    ]`
    0.65
    $}}
    0.62
    ']))
    
    0.61
    Activations Density 0.012%

    No Known Activations