© 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. 21-GEMMASCOPE-RES-16K
    6. 9153
    Prev
    Next
    INDEX
    Explanations

    beginning markers in different document structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    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
    -0.91
    __":
    
    -0.90
    __':
    
    -0.89
    "]),
    -0.88
    '}),
    -0.88
    .”)
    -0.83
    __":
    -0.82
    ")){
    -0.81
    ."),
    -0.80
    IndentedString
    -0.80
    POSITIVE LOGITS
     useSelector
    0.50
    깐
    0.48
    ledem
    0.48
     geweest
    0.45
     blevet
    0.45
    AndGet
    0.45
     maternelle
    0.44
    zoeken
    0.43
    いますが
    0.43
    [];
    
    0.42
    Activations Density 0.226%

    No Known Activations