© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 8396
    Prev
    Next
    INDEX
    Explanations

    markers or symbols associated with references and citations in academic writing

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

    Bracketed citations with numbers

    np_acts-logits-general · gemini-2.0-flash

    citations or references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    تقاوى
    -0.54
    ьаж
    -0.54
    reportWebVitals
    -0.53
    VersionUID
    -0.51
    :✨
    -0.50
     dAtA
    -0.50
    AccessorTable
    -0.48
    Билгалдахарш
    -0.48
    
    -0.48
    )_/¯
    -0.48
    POSITIVE LOGITS
    complexContent
    0.41
    Enllaces
    0.41
    pitaux
    0.39
     Abschluss
    0.39
     conclure
    0.39
    gebung
    0.38
     Rückkehr
    0.37
    Katso
    0.36
    웍
    0.35
    ölkerung
    0.35
    Activations Density 0.484%

    No Known Activations