© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 4286
    Prev
    Next
    INDEX
    Explanations

    medical terminology related to adverse reactions and safety information in drug treatment

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

    "Adverse" or "significant" followed by a medical term

    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 @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gnac
    -0.61
    ########.
    -0.55
    BeginContext
    -0.54
    verture
    -0.53
     encant
    -0.53
    jectories
    -0.53
    Портал
    -0.52
    favicon
    -0.49
    NUMX
    -0.47
    calaure
    -0.47
    POSITIVE LOGITS
     side
    1.50
     Side
    1.32
    Side
    1.30
     SIDE
    1.18
    side
    1.13
     adverse
    1.10
    SIDE
    1.03
     reactions
    0.94
    Adverse
    0.88
     Adverse
    0.87
    Activations Density 0.981%

    No Known Activations