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

    Neuronpedia

    Jacobian LensNEW
    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. 33-GEMMASCOPE-RES-16K
    11. 10133
    Prev
    Next
    INDEX
    Explanations

    language associated with communication, requests, and grievances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.58
    OCCURRED
    -0.58
    CloseOperation
    -0.57
    kháu
    -0.55
    AutoScaleMode
    -0.53
    rungsseite
    -0.52
     oprot
    -0.51
     مشين
    -0.50
     تكبرها
    -0.49
    writeFieldEnd
    -0.49
    POSITIVE LOGITS
     receiving
    3.16
     received
    3.06
     receive
    3.05
     receives
    2.84
     Receiving
    2.78
    receive
    2.69
     Receive
    2.66
    Receiving
    2.63
    receiving
    2.61
    received
    2.59
    Activations Density 0.978%

    No Known Activations