© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 28-GEMMASCOPE-RES-16K
    11. 11756
    Prev
    Next
    INDEX
    Explanations

    references to climate-related events and phenomena

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    Weather conditions; rainfall, cold, drought

    np_acts-logits-general · gemini-2.0-flash

    weather conditions and temperatures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    tagHelperRunner
    -0.60
    oa̍t
    -0.47
    GTCX
    -0.47
     estekak
    -0.44
     program
    -0.39
    Expand
    -0.38
    program
    -0.38
    partiet
    -0.38
     informée
    -0.38
    ausch
    -0.37
    POSITIVE LOGITS
     drought
    0.90
     droughts
    0.77
     winters
    0.75
     storms
    0.75
     winter
    0.74
     meteoro
    0.69
     weather
    0.67
     unprecedented
    0.65
     rainfall
    0.65
     rains
    0.64
    Activations Density 0.186%

    No Known Activations