© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 12935
    Prev
    Next
    INDEX
    Explanations

    infinitive forms of the verb "to."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
     snippetHide
    -0.91
    IsContent
    -0.85
     ComVisible
    -0.81
    出版年
    -0.81
     kasarigan
    -0.81
    iffance
    -0.81
    Билгалдахарш
    -0.80
     indígen
    -0.79
    ſſung
    -0.78
     queſta
    -0.77
    POSITIVE LOGITS
    ↵
    0.45
    .
    0.44
     be
    0.40
    ↵↵
    0.39
     försö
    0.34
     true
    0.33
    ,
    0.32
     The
    0.32
     
    0.32
     major
    0.31
    Activations Density 0.207%

    No Known Activations