© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9000
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to mathematical calculations and operations

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

    "Calculate" and related terms, often in math problems

    np_acts-logits-general · gemini-2.0-flash

    mathematical calculation

    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
     createSprite
    -0.59
     briefly
    -0.47
     brand
    -0.46
    <b>
    -0.45
     brands
    -0.45
     Siegel
    -0.44
     Rood
    -0.44
     Gurney
    -0.44
    rzej
    -0.42
    ˜
    -0.42
    POSITIVE LOGITS
     calculations
    0.94
     Calculations
    0.90
     calculation
    0.90
    Calculations
    0.88
     Calculation
    0.88
    Calculation
    0.85
     computation
    0.84
     computations
    0.84
     calculate
    0.83
    calculation
    0.83
    Activations Density 0.353%

    No Known Activations