Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 1106
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to rainfall and precipitation dynamics

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

    precipitation

    np_acts-logits-general · gemini-2.0-flash

    rain, rainfall, precipitation, storms

    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
    __*/
    -0.70
    RegressionTest
    -0.69
     imagui
    -0.69
    IntoConstraints
    -0.68
    <unused16>
    -0.67
    <unused28>
    -0.66
    <unused51>
    -0.66
    <unused23>
    -0.66
    <pad>
    -0.66
    [@BOS@]
    -0.66
    POSITIVE LOGITS
     rain
    1.01
     rains
    0.83
     rainfall
    0.82
     Rain
    0.78
    Rain
    0.75
     storm
    0.75
     pluie
    0.73
     RAIN
    0.72
     Rainfall
    0.71
    ☔
    0.70
    Activations Density 0.108%

    No Known Activations