© 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. 7068
    Prev
    Next
    INDEX
    Explanations

    structured documentation and formal notation

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

    Section or subsection headings

    np_acts-logits-general · gemini-2.0-flash

    ordering, concluding, or sequencing

    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
     pleaſure
    -1.04
     iſt
    -0.96
    MigrationBuilder
    -0.94
     juſ
    -0.93
     ſind
    -0.93
     ſch
    -0.92
     ſche
    -0.92
     ſever
    -0.92
     ſtate
    -0.91
     faſt
    -0.90
    POSITIVE LOGITS
     
    0.94
     Other
    0.74
     second
    0.73
    Other
    0.69
    Conclusion
    0.69
     other
    0.66
     final
    0.63
    other
    0.62
     third
    0.62
     Conclusion
    0.62
    Activations Density 1.735%

    No Known Activations