© 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-2-9B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 14973
    Prev
    Next
    INDEX
    Explanations

    information about professional roles and organizational structures in clinical and biological contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    complexContent
    -0.43
    setViewportView
    -0.42
    被告
    -0.41
    trường
    -0.41
     iconLine
    -0.40
     worth
    -0.40
    uscht
    -0.38
    ThemeOverlay
    -0.38
     JScrollPane
    -0.38
     ARTICLES
    -0.38
    POSITIVE LOGITS
     staff
    0.97
     staffed
    0.84
    staff
    0.81
     staffing
    0.79
     staffers
    0.74
     team
    0.74
     staffs
    0.72
     office
    0.66
    Staff
    0.66
     specialists
    0.66
    Activations Density 0.245%

    No Known Activations