© 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. 14-GEMMASCOPE-RES-16K
    6. 12424
    Prev
    Next
    INDEX
    Explanations

    phrases related to scientific evidence and research implications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AccessorTable
    -0.88
    Personendaten
    -0.83
     Paglinawan
    -0.83
    исленность
    -0.83
    脚注の使い方
    -0.80
     Monfieur
    -0.79
    ContentAsync
    -0.78
    NUMX
    -0.78
     Roskov
    -0.77
     AssemblyCompany
    -0.77
    POSITIVE LOGITS
     uses
    0.51
     comfortable
    0.48
     or
    0.46
     grazie
    0.43
    he
    0.43
     use
    0.42
    HE
    0.41
     ease
    0.40
     rest
    0.40
     friendly
    0.40
    Activations Density 0.294%

    No Known Activations