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. 25-GEMMASCOPE-RES-16K
    6. 5882
    Prev
    Next
    INDEX
    Explanations

    references to critique or challenge societal norms and beliefs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     poichè
    -0.78
     definately
    -0.71
     coté
    -0.68
    rasında
    -0.67
    非常的
    -0.65
     perchè
    -0.65
    很多的
    -0.62
     didalam
    -0.62
     alot
    -0.61
    凄く
    -0.60
    POSITIVE LOGITS
     intrepid
    0.76
     interminable
    0.76
     semejante
    0.75
     tales
    0.73
     hapless
    0.72
    ècie
    0.72
    WebElementEntity
    0.71
     sleek
    0.71
    adaptiveStyles
    0.70
     yore
    0.70
    Activations Density 0.679%

    No Known Activations