© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 6969
    Prev
    Next
    INDEX
    Explanations

    references to individuals involved in legal situations or criminal charges

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows "was" or "were" and precedes a past participle

    np_acts-logits-general · gemini-2.0-flash

    formal states, appointments, outcomes

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     réalis
    -0.57
    SharedCtor
    -0.46
    inhabited
    -0.42
    jsxFileName
    -0.42
    owali
    -0.41
     gespannt
    -0.41
     σα
    -0.41
    okra
    -0.41
     HÀ
    -0.41
     gustan
    -0.41
    POSITIVE LOGITS
    Pyx
    0.91
     appointed
    0.79
     selected
    0.78
     interviewed
    0.77
     recruited
    0.76
     inducted
    0.76
     invited
    0.75
     placed
    0.70
     hired
    0.69
     brought
    0.69
    Activations Density 0.536%

    No Known Activations