© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 13772
    Prev
    Next
    INDEX
    Explanations

    references to specific medications and their effects

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

    Dosage or concentration expressed in g/kg

    np_acts-logits-general · gemini-2.0-flash

    Gal, solvents, methadone

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    setVerticalGroup
    -0.76
    IntoConstraints
    -0.63
     EconPapers
    -0.59
     estekak
    -0.56
    InstrumentedTest
    -0.52
     beginnetje
    -0.52
    }}],
    -0.52
    WaitGroup
    -0.48
     Chwiliwch
    -0.48
    principalColumn
    -0.47
    POSITIVE LOGITS
    yelidikan
    0.39
    Drew
    0.38
     Drew
    0.37
     gameObject
    0.36
    ytick
    0.35
    addParameter
    0.34
    paket
    0.34
    amazonaws
    0.34
    atoires
    0.34
    意
    0.33
    Activations Density 0.074%

    No Known Activations