© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 95995
    Prev
    Next
    INDEX
    Explanations

    references to academics and bureaucratic systems

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

    academia and bureaucracy

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    iotensin
    -0.60
    MessageTagHelper
    -0.59
    Synonymes
    -0.52
    houette
    -0.50
     consultations
    -0.49
     Fulfillment
    -0.47
    chtenstein
    -0.47
     ultimatum
    -0.46
    therosclerosis
    -0.46
     isomer
    -0.46
    POSITIVE LOGITS
     academics
    1.47
     Aca
    1.28
    Academics
    1.26
    Aca
    0.95
    acade
    0.84
    demics
    0.65
     acadé
    0.59
     aca
    0.55
     scholars
    0.50
    textLabel
    0.48
    Activations Density 0.008%

    No Known Activations