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. 12-GEMMASCOPE-RES-16K
    6. 5961
    Prev
    Next
    INDEX
    Explanations

    terms related to wind and its effects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    addPreferredGap
    -0.83
     Lush
    -0.69
     McRae
    -0.68
     Uts
    -0.67
    Hatch
    -0.64
    عط
    -0.64
     Darmstadt
    -0.62
     Daryl
    -0.62
     McCoy
    -0.62
    orious
    -0.60
    POSITIVE LOGITS
     Wind
    1.70
     wind
    1.67
    Wind
    1.66
    wind
    1.63
     WIND
    1.62
     winds
    1.58
     Winds
    1.50
    WIND
    1.48
    winds
    1.46
     viento
    1.33
    Activations Density 0.080%

    No Known Activations