© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 3066
    Prev
    Next
    INDEX
    Explanations

    references to resignations and signings of documents

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

    resigning or quitting

    np_acts-logits-general · gemini-2.0-flash

    resigning or resignation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     समीक्षाओं
    -0.50
    bootstrapcdn
    -0.50
    vician
    -0.42
    Companion
    -0.41
    enderror
    -0.41
     snaps
    -0.40
     المهم
    -0.40
    PDATE
    -0.40
     Promises
    -0.40
     Revival
    -0.39
    POSITIVE LOGITS
     resignation
    1.21
     resign
    1.09
     démission
    1.06
     resigning
    1.03
    resign
    1.02
     resigned
    0.94
    辞职
    0.85
     quitting
    0.81
     renuncia
    0.78
     quit
    0.76
    Activations Density 0.239%

    No Known Activations