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. 20-GEMMASCOPE-RES-16K
    6. 14050
    Prev
    Next
    INDEX
    Explanations

    contact information and inquiries related to services

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ystem
    -0.58
     system
    -0.46
     secondary
    -0.45
     trừ
    -0.45
    System
    -0.44
    system
    -0.43
    opter
    -0.43
    .='
    -0.42
    とこ
    -0.42
     الاطلاع
    -0.42
    POSITIVE LOGITS
    WebVitals
    0.85
    rungsseite
    0.80
     (+
    0.77
    曖昧さ回避
    0.77
     Tel
    0.76
     StatefulWidget
    0.74
     +
    0.70
    Tel
    0.70
    ConstraintMaker
    0.68
     tel
    0.68
    Activations Density 0.079%

    No Known Activations