© 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-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 80422
    Prev
    Next
    INDEX
    Explanations

    certain types of programming or scripting language elements, particularly related to function calls and error handling

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

    `syscall.Errno` codes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     propOrder
    -0.52
     jspb
    -0.43
    Décès
    -0.34
     useParams
    -0.32
    GeoNames
    -0.31
     Audiodateien
    -0.30
     mergeFrom
    -0.29
     endwhile
    -0.29
    buttonBar
    -0.28
    PageModule
    -0.28
    POSITIVE LOGITS
     Administrativna
    0.69
    Tembelea
    0.65
     gimnasio
    0.63
    
    0.59
    Diweddarwch
    0.56
    Lycka
    0.56
     agência
    0.55
     فريبيس
    0.55
     productivo
    0.55
     EconPapers
    0.54
    Activations Density 0.014%

    No Known Activations