© 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. 9008
    Prev
    Next
    INDEX
    Explanations

    terms related to medical safety, specifically adverse reactions and their monitoring

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

    Adverse drug reactions/side effects

    np_acts-logits-general · gemini-2.0-flash

    adverse reactions and side effects

    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
    脚注の使い方
    -0.73
    IntoConstraints
    -0.68
    InjectMocks
    -0.61
     autorytatywna
    -0.54
    ########.
    -0.54
     Falta
    -0.53
     gql
    -0.52
    TintMode
    -0.51
    BeginContext
    -0.51
    знес
    -0.50
    POSITIVE LOGITS
     side
    1.01
     Side
    0.94
    Side
    0.87
     SIDE
    0.82
     adverse
    0.80
    副作用
    0.78
    SIDE
    0.77
     reactions
    0.74
    side
    0.72
     Nebenwirkungen
    0.69
    Activations Density 0.699%

    No Known Activations