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. 12816
    Prev
    Next
    INDEX
    Explanations

    terms related to governance and board membership

    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
    expandindo
    -0.66
    EMPO
    -0.63
    RequiresApi
    -0.55
    kirche
    -0.53
    copi
    -0.53
    లాలు
    -0.53
    мпу
    -0.52
    setContentView
    -0.52
     оригіналу
    -0.52
    itals
    -0.52
    POSITIVE LOGITS
     committee
    0.90
     board
    0.89
     committees
    0.87
     panel
    0.85
     Board
    0.80
     Committee
    0.72
     trustees
    0.70
     Panel
    0.70
    panel
    0.69
     subcommittee
    0.69
    Activations Density 0.246%

    No Known Activations