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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 8419
    Prev
    Next
    INDEX
    Explanations

    references to scheduling or making appointments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     @"/
    -0.44
    UnusedPrivate
    -0.41
    ResponseWriter
    -0.38
     doInBackground
    -0.37
    WebServlet
    -0.37
    ThroughAttribute
    -0.36
     []:
    -0.34
     contenta
    -0.34
    badlogic
    -0.33
     Huff
    -0.33
    POSITIVE LOGITS
     trustees
    0.99
     trustee
    0.96
     shareholders
    0.94
     Trustees
    0.92
     Trustee
    0.90
     donors
    0.88
     shareholder
    0.87
     Shareholders
    0.86
     donor
    0.86
     volunteer
    0.85
    Activations Density 0.113%

    No Known Activations