© 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. 2-GEMMASCOPE-RES-16K
    6. 7514
    Prev
    Next
    INDEX
    Explanations

    repetitive uses of the word "all" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Архівовано
    -0.80
    出版年
    -0.73
    Życiorys
    -0.72
     insuffisamment
    -0.71
    )‏
    -0.71
    numerusform
    -0.70
     useRouter
    -0.68
     '\\;'
    -0.66
    ioneer
    -0.66
     disambiguazione
    -0.65
    POSITIVE LOGITS
    all
    3.53
    ALL
    3.06
    All
    2.46
     All
    2.29
    alls
    2.22
     ALL
    2.22
     all
    2.19
    allin
    1.62
     alls
    1.61
     GetAll
    1.48
    Activations Density 0.135%

    No Known Activations