© 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-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 1702
    Prev
    Next
    INDEX
    Explanations

    phrases related to reducing or minimizing various factors, such as costs, risks, or physical quantities

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

    Lowering costs or reducing risks

    np_acts-logits-general · gemini-2.0-flash

    reducing quantity or cost

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     تضيفلها
    -0.87
     للمعارف
    -0.65
     OMITTED
    -0.62
     дописавши
    -0.61
    存于互联网档案馆
    -0.60
     ComVisible
    -0.60
     Meksiku
    -0.59
    żesz
    -0.59
    ThroughAttribute
    -0.58
     surla
    -0.56
    POSITIVE LOGITS
     costs
    0.97
     cost
    0.84
     footprint
    0.81
    costs
    0.75
    cost
    0.74
     Costs
    0.72
     Footprint
    0.72
     risk
    0.69
     COSTS
    0.68
     risks
    0.68
    Activations Density 0.384%

    No Known Activations