Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 19-GEMMASCOPE-RES-16K
    6. 308
    Prev
    Next
    INDEX
    Explanations

    references to political figures and their roles

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.85
    
    -0.74
    DockStyle
    -0.74
    tagext
    -0.64
    StoryboardSegue
    -0.62
     MainAxisSize
    -0.62
     Parent
    -0.62
     emperors
    -0.62
    BeginContext
    -0.59
     Pingback
    -0.57
    POSITIVE LOGITS
     advisers
    1.00
     assistant
    0.98
     advisors
    0.97
     aide
    0.96
     adviser
    0.95
    advis
    0.95
     assistants
    0.93
     advisor
    0.92
     confid
    0.92
     aides
    0.92
    Activations Density 0.305%

    No Known Activations