Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & 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. 2327
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "link" and its related forms

    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
    -0.93
     MainAxisSize
    -0.80
     للمعارف
    -0.80
    typescript
    -0.79
    dafx
    -0.73
     forfait
    -0.72
    cabulary
    -0.71
    ModelAdmin
    -0.71
     sopr
    -0.71
    newState
    -0.71
    POSITIVE LOGITS
     link
    2.42
     links
    2.33
     Link
    2.22
     LINK
    2.16
     Links
    2.08
    links
    2.06
    link
    2.02
    Link
    2.00
     LINKS
    1.92
    LINK
    1.90
    Activations Density 0.048%

    No Known Activations