© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 10515
    Prev
    Next
    INDEX
    Explanations

    phrases related to significant life events and the emotions or actions surrounding them

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.66
    setViewportView
    -0.63
    rungsseite
    -0.61
    ArgsConstructor
    -0.60
     initComponents
    -0.59
    GenerationType
    -0.58
     pad
    -0.58
    ValueStyle
    -0.57
     PAD
    -0.57
    AutoresizingMask
    -0.57
    POSITIVE LOGITS
     damals
    2.15
    当时的
    1.92
    当时
    1.91
    當時
    1.90
    那时候
    1.85
     тогда
    1.82
    那时
    1.78
     Тогда
    1.74
     damaligen
    1.74
    当時は
    1.67
    Activations Density 0.543%

    No Known Activations