© 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. 3553
    Prev
    Next
    INDEX
    Explanations

    references to specific chemical compounds and their effects on plants

    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
    LookAnd
    -0.67
    ThroughAttribute
    -0.59
    MessageOf
    -0.57
    setCellStyle
    -0.51
     ujednoznacz
    -0.50
    bitField
    -0.47
    RuleContext
    -0.47
     HasFactory
    -0.46
    windowFixed
    -0.45
    GEBURTSDATUM
    -0.45
    POSITIVE LOGITS
     plants
    2.59
     plant
    2.27
    plants
    2.09
     Plants
    2.09
    Plants
    2.00
     plantas
    1.93
     PLANTS
    1.92
    plant
    1.84
     Plant
    1.77
    植物
    1.73
    Activations Density 0.448%

    No Known Activations