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. 14243
    Prev
    Next
    INDEX
    Explanations

    instances of the word "final" and its derivatives

    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
     wireType
    -0.72
    ніципалі
    -0.70
    ⋙
    -0.68
    rungsseite
    -0.67
     cioè
    -0.67
    aiuto
    -0.65
     guste
    -0.65
    igers
    -0.65
     McClure
    -0.65
     refaire
    -0.64
    POSITIVE LOGITS
     Final
    2.00
    Final
    1.95
     FINAL
    1.94
     final
    1.93
    FINAL
    1.86
    final
    1.79
     finals
    1.42
     Finals
    1.39
    finals
    1.24
     finales
    1.22
    Activations Density 0.086%

    No Known Activations