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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 1011
    Prev
    Next
    INDEX
    Explanations

    entities related to political leaders and their actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     COVID
    -1.49
     covid
    -1.40
     Covid
    -1.36
    COVID
    -1.31
    covid
    -1.30
     https
    -1.30
    https
    -1.28
     TikTok
    -1.20
    Covid
    -1.20
     nullptr
    -1.14
    POSITIVE LOGITS
     idéia
    1.34
    myspace
    1.12
     = 
    1.06
     iPod
    1.02
    berdayakan
    0.99
     ipod
    0.99
     daß
    0.96
     Arxivat
    0.93
     MySpace
    0.92
     muß
    0.92
    Activations Density 8.976%

    No Known Activations