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. 6027
    Prev
    Next
    INDEX
    Explanations

    functional elements of programming code, particularly related to defining functions and handling data structures

    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
     Oil
    -0.76
     Skin
    -0.74
     Water
    -0.74
     Food
    -0.73
     Wine
    -0.72
     Hair
    -0.71
     Fish
    -0.71
     Meat
    -0.70
     Coffee
    -0.68
     Alcohol
    -0.68
    POSITIVE LOGITS
    Билгалдахарш
    0.60
     surla
    0.58
    TagMode
    0.57
    hamshire
    0.50
    abestanden
    0.49
    inander
    0.49
    netbeans
    0.48
    EDEFAULT
    0.48
    yanka
    0.47
    kloped
    0.47
    Activations Density 0.563%

    No Known Activations