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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 8-GEMMASCOPE-RES-16K
    6. 2019
    Prev
    Next
    INDEX
    Explanations

    references to cold temperatures and winter-related conditions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     nakalista
    -0.81
    Enllaços
    -0.70
    nlm
    -0.62
     Aug
    -0.56
    ypep
    -0.56
     Ex
    -0.55
    BitmapFactory
    -0.53
    Tikang
    -0.53
     June
    -0.52
     Guil
    -0.52
    POSITIVE LOGITS
     freezing
    0.97
     cold
    0.96
     freeze
    0.95
     winter
    0.94
     Freezing
    0.93
     frost
    0.93
     freezes
    0.92
     winters
    0.91
     arctic
    0.91
    cold
    0.90
    Activations Density 0.408%

    No Known Activations