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. 5-GEMMASCOPE-RES-16K
    6. 14301
    Prev
    Next
    INDEX
    Explanations

    the start of a new document or section within a text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.84
    Datuak
    -0.79
     BoxFit
    -0.77
    AccessFile
    -0.74
     nahilalakip
    -0.74
     ModelAndView
    -0.74
    CloseOperation
    -0.71
    usercontent
    -0.70
     Signalez
    -0.69
     محفوظة
    -0.69
    POSITIVE LOGITS
    ↵↵
    1.09
    ↵
    1.06
    ↵↵↵
    0.73
    ↵↵↵↵
    0.65
    aarrggbb
    0.61
    </tr>
    0.60
    <eos>
    0.59
    例文帳に追加
    0.59
    <bos>
    0.56
    ')),
    0.56
    Activations Density 0.369%

    No Known Activations