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-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 3251
    Prev
    Next
    INDEX
    Explanations

    terms related to coldness

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

    The token "cold"

    np_acts-logits-general · gemini-2.0-flash

    cold atoms, Cold War, cold pressed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 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
     CreateTagHelper
    -0.89
    GEBURTSDATUM
    -0.81
    BeginContext
    -0.78
     normaux
    -0.75
    XmlAccessorType
    -0.74
    ViewFeatures
    -0.74
     ujednoznacz
    -0.74
     MainAxisSize
    -0.73
     magasiner
    -0.71
    bootstrapcdn
    -0.70
    POSITIVE LOGITS
     Cold
    0.77
     weather
    0.75
    Cold
    0.72
     cold
    0.71
     COLD
    0.71
    COLD
    0.69
    blooded
    0.60
    cold
    0.59
    WARM
    0.57
     blo
    0.57
    Activations Density 0.054%

    No Known Activations