© 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. 1346
    Prev
    Next
    INDEX
    Explanations

    instances of complaints and allegations related to misconduct

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

    Texts about accusations or grievances

    np_acts-logits-general · gemini-2.0-flash

    complaints and allegations

    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
    UrlResolution
    -0.59
     snippetHide
    -0.54
    DockStyle
    -0.53
     FileWriter
    -0.52
     Rink
    -0.48
    richTextPanel
    -0.45
     Piers
    -0.44
    RRect
    -0.43
     useAppContext
    -0.43
    Tembelea
    -0.43
    POSITIVE LOGITS
     complaints
    1.02
     complaint
    0.97
     complained
    0.88
     complains
    0.84
     Complaints
    0.82
     complain
    0.82
    Complaints
    0.80
     complaining
    0.78
    complaint
    0.78
     Complaint
    0.74
    Activations Density 0.307%

    No Known Activations