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. 1292
    Prev
    Next
    INDEX
    Explanations

    references to academic proceedings and citations in scientific literature

    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
     Theſe
    -0.81
    __':
    
    -0.80
     Reſ
    -0.72
     Jefus
    -0.71
     Monfieur
    -0.70
     Majefty
    -0.70
     ſeveral
    -0.67
     ſte
    -0.67
     myſelf
    -0.67
     juſ
    -0.66
    POSITIVE LOGITS
    <bos>
    0.70
    Eds
    0.67
    Hrsg
    0.65
    copyWith
    0.55
     eds
    0.54
    клопе
    0.53
     estimés
    0.53
     kasarigan
    0.51
     跳转至
    0.49
     NSCoder
    0.48
    Activations Density 0.208%

    No Known Activations