© 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. 7903
    Prev
    Next
    INDEX
    Explanations

    patterns related to punctuation and their impact on string processing

    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
    localctx
    -0.80
    ']")
    -0.75
    ")));
    
    -0.74
    ')")
    -0.73
     defaultstate
    -0.72
     ""))
    -0.71
    '))
    
    -0.69
    '")
    -0.69
    })*/
    -0.69
     GenerationType
    -0.69
    POSITIVE LOGITS
     spaces
    1.19
     space
    1.16
    space
    1.04
     dashes
    1.02
     Spaces
    1.01
     Space
    1.01
     dash
    1.01
     SPACE
    1.00
     dot
    0.99
    spaces
    0.99
    Activations Density 0.897%

    No Known Activations