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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlog/PodcastSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlog/PodcastGitHubSlackTwitterContact
    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. 2027
    Prev
    Next
    INDEX
    Explanations

    references to wind-related concepts and technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ItemBackground
    -0.66
    DebuggerNonUser
    -0.59
     Dropout
    -0.57
     SafeMath
    -0.56
    simo
    -0.56
     betweenstory
    -0.54
     utafitiHapana
    -0.53
    Deco
    -0.52
     /\.(
    -0.51
    zaron
    -0.50
    POSITIVE LOGITS
     wind
    1.12
     Wind
    1.09
    Wind
    1.01
     WIND
    1.01
     winds
    0.98
     Winds
    0.97
     blowing
    0.97
     gusts
    0.96
    wind
    0.93
    Winds
    0.91
    Activations Density 0.056%

    No Known Activations