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. 12-GEMMASCOPE-RES-16K
    6. 1970
    Prev
    Next
    INDEX
    Explanations

    instances of the word "different" and its variations, focusing on changes and distinctions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     umana
    -1.01
     vectorielle
    -0.98
     picioare
    -0.92
     humaine
    -0.91
     étoient
    -0.88
     umane
    -0.87
     nucléaire
    -0.87
     humaines
    -0.86
     poitrine
    -0.86
     vectorielles
    -0.85
    POSITIVE LOGITS
     different
    1.16
    Different
    1.10
     DIFFERENT
    1.06
     Different
    1.05
    different
    0.99
     difer
    0.95
     kinds
    0.94
     diff
    0.83
    ferent
    0.81
     departments
    0.81
    Activations Density 0.082%

    No Known Activations