© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 34-GEMMASCOPE-RES-16K
    11. 4243
    Prev
    Next
    INDEX
    Explanations

    medical warnings and safety information related to drug usage and side effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    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
    -0.55
     disambiguazione
    -0.51
    #+#
    -0.50
    AnchorStyles
    -0.50
    SpringRunner
    -0.49
     GenerationType
    -0.48
    PrototypeOf
    -0.48
     ModelExpression
    -0.47
    thenReturn
    -0.47
    ftagPool
    -0.46
    POSITIVE LOGITS
     side
    1.15
     adverse
    1.15
     Nebenwirkungen
    1.05
    副作用
    1.03
    Adverse
    1.03
     Adverse
    0.98
     Side
    0.97
    Side
    0.97
     SIDE
    0.95
     побо
    0.93
    Activations Density 1.046%

    No Known Activations