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

    Neuronpedia

    APICircuit 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. 12-GEMMASCOPE-RES-16K
    6. 4554
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and technical terminology in complex scientific or technical documents

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -1.19
     Chwiliwch
    -1.05
    tagHelperRunner
    -1.02
     صوتيه
    -1.02
    endphp
    -1.00
     OnInit
    -0.98
    Datuak
    -0.96
    parsedMessage
    -0.95
    NUMX
    -0.91
     nahilalakip
    -0.91
    POSITIVE LOGITS
    ↵
    1.00
    ↵↵
    0.98
    <eos>
    0.87
     
    0.81
     The
    0.76
        
    0.76
    <tr>
    0.73
    ↵↵↵
    0.72
    ↵↵↵↵
    0.67
    <h2>
    0.65
    Activations Density 0.004%

    No Known Activations