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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 14552
    Prev
    Next
    INDEX
    Explanations

    references to cold weather and winter conditions

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

    Winter, snow, and cold weather

    np_acts-logits-general · gemini-2.0-flash

    winter snow cold weather

    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
    BASEPATH
    -0.60
     lipca
    -0.57
    verwijspagina
    -0.54
    TargetException
    -0.49
    TypedDataSet
    -0.48
     descomp
    -0.47
     initComponents
    -0.47
     JULY
    -0.46
     iulie
    -0.46
     intptr
    -0.46
    POSITIVE LOGITS
     winter
    1.26
    Winter
    1.19
     Winter
    1.16
    winter
    1.10
     WINTER
    1.07
     winters
    1.03
    WINTER
    0.96
     invern
    0.94
     snow
    0.91
     cold
    0.90
    Activations Density 0.405%

    No Known Activations