© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 12-GEMMASCOPE-RES-16K
    11. 14566
    Prev
    Next
    INDEX
    Explanations

    quantitative data and statistics related to populations and health impacts

    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
     AspNetCore
    -0.91
    AnchorStyles
    -0.72
    AccessorTable
    -0.62
    存于互联网档案馆
    -0.62
     Chwiliwch
    -0.61
     ESQ
    -0.60
     adipis
    -0.60
    ImageContext
    -0.59
     stället
    -0.58
     ivelany
    -0.58
    POSITIVE LOGITS
     millions
    1.19
    Millions
    1.15
    millions
    1.08
     billions
    1.02
     Millions
    1.01
     millones
    0.91
     jutaan
    0.88
     milhões
    0.88
     milliards
    0.84
     thousands
    0.74
    Activations Density 0.314%

    No Known Activations