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. 5-GEMMASCOPE-RES-16K
    6. 3822
    Prev
    Next
    INDEX
    Explanations

    negative assertions or phrases that convey a lack of something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.99
     myſelf
    -0.83
     Cæsar
    -0.83
     quæ
    -0.81
     ſeveral
    -0.77
     respeito
    -0.75
     Monfieur
    -0.72
     raiſ
    -0.72
     ejus
    -0.72
     itſelf
    -0.71
    POSITIVE LOGITS
     no
    1.20
     No
    0.87
     нет
    0.83
    Нет
    0.79
     keine
    0.78
    igno
    0.74
    no
    0.73
     ไม่มี
    0.70
     NO
    0.70
     geen
    0.69
    Activations Density 0.127%

    No Known Activations