© 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
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 105648
    Prev
    Next
    INDEX
    Explanations

    requests for assistance or feedback

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    thâu
    -0.63
     autorytatywna
    -0.63
     nahilalakip
    -0.60
    haikusbot
    -0.56
    PostInfinity
    -0.56
    AdapterView
    -0.55
    forChild
    -0.55
    :][
    -0.54
    点此举报
    -0.54
     ujednoznacz
    -0.54
    POSITIVE LOGITS
     appreciated
    0.40
     मदद
    0.39
     Help
    0.38
     Please
    0.37
     segíts
    0.37
     please
    0.36
     Kindly
    0.36
     assist
    0.36
     HELP
    0.35
     kindly
    0.35
    Activations Density 0.016%

    No Known Activations