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. 5945
    Prev
    Next
    INDEX
    Explanations

    references to video game mechanics and strategies

    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
    tagHelperRunner
    -0.71
    RTDA
    -0.57
     OBB
    -0.56
    verwijspagina
    -0.56
    SwingConstants
    -0.56
     Weston
    -0.54
    fjspx
    -0.53
    mybatisplus
    -0.53
    DoubleQuotes
    -0.53
    isEmail
    -0.52
    POSITIVE LOGITS
     lane
    0.73
     champions
    0.72
     jung
    0.72
     ADC
    0.71
     jungle
    0.68
     champion
    0.67
     adc
    0.66
     League
    0.63
     lanes
    0.62
     Yas
    0.62
    Activations Density 0.133%

    No Known Activations