© 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. 9-GEMMASCOPE-RES-16K
    6. 7175
    Prev
    Next
    INDEX
    Explanations

    references to data manipulation techniques in a scientific or technical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     مشين
    -0.90
     كومونز
    -0.66
    ỳnh
    -0.66
     سكانية
    -0.63
    itário
    -0.63
    InputBorder
    -0.63
    — 
    -0.62
    SBATCH
    -0.61
     synag
    -0.59
    ̩
    -0.59
    POSITIVE LOGITS
    SourceChecksum
    0.74
    :"-"`
    0.62
    ivis
    0.60
     
    0.59
       
    0.56
      
    0.56
    ')['
    0.52
     наоборот
    0.52
    ?
    0.51
    StoreMessageInfo
    0.50
    Activations Density 1.602%

    No Known Activations