© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 126284
    Prev
    Next
    INDEX
    Explanations

    terms related to "copy number" variations in genetic sequences

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

    copy number variation

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    isNotNull
    -0.60
    esgue
    -0.59
     HttpStatus
    -0.57
    PreExecute
    -0.55
     OnInit
    -0.54
    SwingConstants
    -0.53
    estrel
    -0.53
     Nordstrom
    -0.52
     viewDidLoad
    -0.52
     getName
    -0.51
    POSITIVE LOGITS
     copy
    1.28
    copy
    1.16
     COPY
    1.15
    Copy
    1.15
     Copy
    1.09
     copies
    1.05
    COPY
    1.02
     copia
    1.00
     Copies
    0.92
     copie
    0.92
    Activations Density 0.018%

    No Known Activations