© 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 - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6711
    Prev
    Next
    INDEX
    Explanations

    references to natural substances or compounds and their applications or implications in various fields, particularly health and fitness

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

    frequently preceding periods or commas

    np_acts-logits-general · gemini-2.0-flash

    widespread populations, cells, traditions

    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-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    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
    PerformLayout
    -0.67
    ⤹
    -0.54
    tanleria
    -0.54
     betweenstory
    -0.53
    ifikationer
    -0.52
     transférez
    -0.52
     المعيارى
    -0.50
    
    -0.50
    batore
    -0.50
    ↹
    -0.49
    POSITIVE LOGITS
    @[+][
    0.42
     widespread
    0.38
    ultades
    0.38
     widely
    0.32
    sillos
    0.31
     muualla
    0.30
     hivat
    0.30
    广
    0.30
     دیکھیے
    0.29
     among
    0.29
    Activations Density 0.799%

    No Known Activations