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. 15-GEMMASCOPE-RES-16K
    6. 12578
    Prev
    Next
    INDEX
    Explanations

    patterns resembling structured data or code segments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HtmlAttribute
    -1.09
     Paglinawan
    -1.04
    Geplaatst
    -1.00
    sizeCache
    -0.98
    下载附件
    -0.95
     AssemblyCompany
    -0.95
     通販
    -0.93
     Italijani
    -0.92
    principalColumn
    -0.91
    SequentialGroup
    -0.91
    POSITIVE LOGITS
    以上の
    0.58
    此外
    0.51
    '
    0.51
    .
    0.47
    Finally
    0.46
    <eos>
    0.46
    ↵↵
    0.46
    return
    0.46
     més
    0.45
    <tr>
    0.45
    Activations Density 0.173%

    No Known Activations