© 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. 39-GEMMASCOPE-RES-16K
    11. 697
    Prev
    Next
    INDEX
    Explanations

    references to past events or experiences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ToBounds
    -0.40
    脚注の使い方
    -0.34
     aprendizagem
    -0.34
    下载附件
    -0.33
    Tembelea
    -0.32
    ništ
    -0.31
     speziell
    -0.30
    AccessorTable
    -0.30
    ModelAdmin
    -0.30
     ويكيميديا
    -0.30
    POSITIVE LOGITS
     errands
    1.22
     appointments
    1.12
     errand
    0.91
     chores
    0.91
     Appointments
    0.90
     appointment
    0.90
    appointments
    0.88
     meetings
    0.87
     groceries
    0.86
     grocery
    0.85
    Activations Density 0.543%

    No Known Activations