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. 25-GEMMASCOPE-RES-16K
    6. 5801
    Prev
    Next
    INDEX
    Explanations

    references to meals, particularly lunch and dinner

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    PerformLayout
    -0.70
    LayoutConstraint
    -0.67
    
    -0.64
     StringVar
    -0.58
    êmios
    -0.54
    psons
    -0.53
     breakfast
    -0.52
    InputModule
    -0.50
    bbs
    -0.49
    PostInfinity
    -0.49
    POSITIVE LOGITS
    mybatisplus
    0.78
    time
    0.74
     hour
    0.66
    TIME
    0.65
    タイム
    0.62
    pail
    0.61
    시간
    0.59
    anskje
    0.58
    times
    0.58
    Time
    0.56
    Activations Density 0.162%

    No Known Activations