© 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. 18-GEMMASCOPE-RES-16K
    6. 9474
    Prev
    Next
    INDEX
    Explanations

    references to medical conditions and their management

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

    Pregnancy and birth-related terms

    np_acts-logits-general · gemini-2.0-flash

    multiple births or preterm delivery

    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
    MessageTagHelper
    -0.64
     ſte
    -0.54
     houſe
    -0.54
     ſtand
    -0.53
     faſt
    -0.51
    harusnya
    -0.50
    setColumns
    -0.50
     aprobado
    -0.49
    ñora
    -0.49
     purpoſe
    -0.49
    POSITIVE LOGITS
     twins
    1.26
     twin
    1.16
     Twins
    1.09
     Twin
    1.06
    twin
    1.05
    Twin
    1.04
    Twins
    0.92
     premature
    0.91
     fraternal
    0.81
     triplets
    0.78
    Activations Density 0.201%

    No Known Activations