© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 14582
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terms related to image processing and signal filtering.

    oai_token-act-pair · gpt-3.5-turboTriggered by @bot

    phrases related to trade-offs or costs associated with benefits or advantages. The neuron activates strongly for phrases like "at the cost", "at the expense", "at the price", etc., which indicate a drawback or negative consequence that comes along with some positive outcome or gain.

    oai_token-act-pair · claude-3-5-sonnet-20240620Triggered by @bot

    financial consequences and implications of decisions.

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

    preceding "cost" or "expense"

    np_acts-logits-general · gemini-2.0-flash

    at the cost of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
    Enllaces
    -0.61
    UIControlState
    -0.59
    τως
    -0.55
    Hozzáférés
    -0.54
    drawSprites
    -0.48
    ReusableCell
    -0.48
    AsUp
    -0.48
     Obtén
    -0.47
     unbroken
    -0.47
     ruff
    -0.46
    POSITIVE LOGITS
     expense
    1.67
     at
    1.32
     Expense
    1.27
    expense
    1.23
     cost
    1.17
     kosz
    1.12
     Kosten
    1.08
     expenses
    1.04
     Cost
    1.02
    Expense
    0.99
    Activations Density 0.171%

    No Known Activations