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. 1308
    Prev
    Next
    INDEX
    Explanations

    the word "so" used in various contexts

    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
     myſelf
    -1.04
     itſelf
    -1.03
    ſelves
    -1.01
    --
    
    -1.00
     himſelf
    -0.96
    ſelf
    -0.94
     themſelves
    -0.93
     Efq
    -0.92
    SBATCH
    -0.91
    ();)
    -0.91
    POSITIVE LOGITS
    So
    1.98
     So
    1.92
    so
    1.34
     SO
    1.26
    SO
    1.23
     so
    1.11
    Quindi
    0.99
    Sooo
    0.96
     Quindi
    0.85
    Então
    0.82
    Activations Density 0.081%

    No Known Activations