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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 9813
    Prev
    Next
    INDEX
    Explanations

    mentions of online platforms and services related to social networking and entertainment

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    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
    -0.68
    Personensuche
    -0.67
     pandemic
    -0.66
     ddelweddau
    -0.65
     Covid
    -0.62
     covid
    -0.62
    covid
    -0.57
     يتيمه
    -0.57
    BufferException
    -0.56
     SPDX
    -0.56
    POSITIVE LOGITS
     AOL
    0.82
     MSN
    0.80
     MySpace
    0.77
    MSN
    0.74
     Yahoo
    0.74
     Sites
    0.73
    Yahoo
    0.72
    myspace
    0.68
     yahoo
    0.67
     sites
    0.67
    Activations Density 0.275%

    No Known Activations