© 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. 10775
    Prev
    Next
    INDEX
    Explanations

    discussions about interactions and relationships between different concepts or entities

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

    "interplay" and "between" appearing together

    np_acts-logits-general · gemini-2.0-flash

    interplay between

    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
     kasarigan
    -0.64
     الرياضيه
    -0.62
     canst
    -0.52
     티즈
    -0.51
    ligibility
    -0.50
    ionization
    -0.50
    styleType
    -0.49
    nastics
    -0.48
    HandlerContext
    -0.48
     للمعارف
    -0.48
    POSITIVE LOGITS
     between
    1.00
     Between
    0.80
    between
    0.80
    Between
    0.77
     BETWEEN
    0.75
     mellan
    0.73
     tussen
    0.73
     antara
    0.72
     mellem
    0.71
     между
    0.71
    Activations Density 0.813%

    No Known Activations