© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 12235
    Prev
    Next
    INDEX
    Explanations

    phrases related to adverse drug reactions and safety information

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

    "Adverse events" or side effects

    np_acts-logits-general · gemini-2.0-flash

    adverse events and side effects

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ConstraintMaker
    -0.68
     ModelExpression
    -0.64
     HasFactory
    -0.60
     disambiguazione
    -0.56
     GenerationType
    -0.53
    AnchorStyles
    -0.50
     estekak
    -0.49
     مشين
    -0.48
    Externé
    -0.47
    IntoConstraints
    -0.47
    POSITIVE LOGITS
     adverse
    1.05
     Nebenwirkungen
    1.02
     side
    0.98
    Adverse
    0.97
    副作用
    0.95
     Adverse
    0.91
     побо
    0.85
    Side
    0.84
     Side
    0.82
     SIDE
    0.77
    Activations Density 1.164%

    No Known Activations