© 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-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 13345
    Prev
    Next
    INDEX
    Explanations

    syntax-related structures in code snippets

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

    Closing parenthesis

    np_acts-logits-general · gemini-2.0-flash

    code punctuation and structure

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Theſe
    -1.47
     Monfieur
    -1.34
     myſelf
    -1.31
     itſelf
    -1.29
     becauſe
    -1.23
     themſelves
    -1.23
     auffi
    -1.22
     himſelf
    -1.20
     whoſe
    -1.20
     Jefus
    -1.19
    POSITIVE LOGITS
    <unused63>
    0.61
    <unused62>
    0.59
    <unused61>
    0.58
    ↵↵
    0.54
     
    0.53
    ↵
    0.53
    1
    0.52
    <unused60>
    0.52
      
    0.52
    .
    0.51
    Activations Density 0.505%

    No Known Activations