© 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. 4232
    Prev
    Next
    INDEX
    Explanations

    specific programming constructs and keywords related to functions, variables, and data manipulation

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

    Preceding "Died" or "Reached"

    np_acts-logits-general · gemini-2.0-flash

    Just X / No X / X Done

    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
     murni
    -0.39
     OnInit
    -0.35
     given
    -0.34
     cumplido
    -0.34
     spreken
    -0.33
     driven
    -0.33
    retudo
    -0.33
     demikian
    -0.33
    而来
    -0.32
     terecht
    -0.32
    POSITIVE LOGITS
    лтамалар
    0.79
     ویکی‌پدی
    0.70
     мәкал
    0.67
    OGND
    0.65
    thâu
    0.65
    ItemBackground
    0.65
     betweenstory
    0.64
    MessageOf
    0.63
    Diwedd
    0.63
     Numerade
    0.63
    Activations Density 0.706%

    No Known Activations