© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 9069
    Prev
    Next
    INDEX
    Explanations

    references to tragic historical events and their human impacts

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

    death, violence, and abuse

    np_acts-logits-general · gemini-2.0-flash

    death and victims

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     CreateTagHelper
    -0.63
    httphttps
    -0.62
    цездатний
    -0.60
    ftagPool
    -0.60
     autorytatywna
    -0.60
    rawDesc
    -0.59
    fjspx
    -0.57
    الحياه
    -0.57
     ProtoMessage
    -0.56
     సౌకర్య
    -0.56
    POSITIVE LOGITS
     death
    0.45
     HIV
    0.43
    HIV
    0.42
     symptoms
    0.41
     horrific
    0.40
     victims
    0.40
     deaths
    0.39
    victim
    0.38
    death
    0.37
    Victim
    0.37
    Activations Density 0.997%

    No Known Activations