© 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. 18-GEMMASCOPE-RES-16K
    11. 10330
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and their context within sentences

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

    Sentences ending in a period

    np_acts-logits-general · gemini-2.0-flash

    end of clause punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ^(@)
    -1.33
     myſelf
    -1.28
    ſelves
    -1.13
     Efq
    -1.12
    MigrationBuilder
    -1.09
     itſelf
    -1.08
    Vidite
    -1.06
     pleaſure
    -1.05
     للمعارف
    -1.05
     Jefus
    -1.04
    POSITIVE LOGITS
    ↵↵
    1.00
    ↵
    0.95
    </blockquote>
    0.93
    ↵↵↵
    0.84
     
    0.83
    </strong>
    0.75
    </b>
    0.75
    ↵↵↵↵
    0.74
      
    0.73
    ↵↵↵↵↵
    0.72
    Activations Density 2.542%

    No Known Activations