© 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. 22-GEMMASCOPE-RES-16K
    6. 11579
    Prev
    Next
    INDEX
    Explanations

    punctuation and symbols associated with code syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Enclosed by parentheses or brackets

    np_acts-logits-general · gemini-2.0-flash

    closing punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.90
    '],
    
    -0.76
    '):
    
    -0.74
    '},
    
    -0.70
    ']=$
    -0.68
    ')):
    -0.66
    '}>
    -0.66
    "):
    
    -0.65
    )।
    -0.65
    `,
    
    -0.65
    POSITIVE LOGITS
     Picchu
    0.65
    TemporalType
    0.64
     Wikimedijinoj
    0.61
    OrNil
    0.57
    oblastoma
    0.57
    MessageTagHelper
    0.56
     +
    0.55
     TextAlign
    0.54
     Kenobi
    0.54
    elemField
    0.54
    Activations Density 0.058%

    No Known Activations