© 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. 20-GEMMASCOPE-RES-16K
    11. 4582
    Prev
    Next
    INDEX
    Explanations

    phrases related to job descriptions and qualifications in nursing roles

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

    job listings for nursing positions, with a focus on healthcare staff roles and responsibilities.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
    ProcessEvent
    -0.56
     autorytatywna
    -0.53
    IndentedString
    -0.52
    uxedo
    -0.50
    örgy
    -0.50
    openConnection
    -0.50
    opoly
    -0.49
    Coordonnées
    -0.49
    TagMode
    -0.49
    rifuge
    -0.49
    POSITIVE LOGITS
     resourceCulture
    0.34
     abiertos
    0.31
     vielmehr
    0.30
     régle
    0.30
    étit
    0.30
     aktuell
    0.29
    σθαι
    0.29
     actuelles
    0.28
     directora
    0.28
    *}
    0.28
    Activations Density 0.029%

    No Known Activations