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. 13-GEMMASCOPE-RES-16K
    6. 35
    Prev
    Next
    INDEX
    Explanations

    references to political topics or entities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     
    -0.57
    i
    -0.50
    Autowired
    -0.49
     p
    -0.47
    p
    -0.46
    g
    -0.44
      
    -0.43
     ra
    -0.43
     l
    -0.43
     van
    -0.42
    POSITIVE LOGITS
     Roskov
    1.18
    SharedCtor
    1.07
     myſelf
    1.06
     ſtate
    1.03
     pleaſure
    1.01
     itſelf
    0.98
     MenuView
    0.98
     fubject
    0.97
    ſelf
    0.97
     juſ
    0.96
    Activations Density 0.232%

    No Known Activations