© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 25-GEMMASCOPE-RES-16K
    6. 15546
    Prev
    Next
    INDEX
    Explanations

    terms related to organizational structure and operational roles within organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_25/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.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    queryInterface
    -0.47
     Th
    -0.37
     Es
    -0.36
     Ap
    -0.35
     l
    -0.34
    xlim
    -0.34
     localObject
    -0.34
    Seeder
    -0.33
     Wh
    -0.33
     जाते
    -0.33
    POSITIVE LOGITS
     Grüsse
    0.58
    tvguidetime
    0.58
    SourceChecksum
    0.55
     Geiſt
    0.52
    ########.
    0.50
    himovic
    0.50
     mutiara
    0.49
     muco
    0.48
     adesivos
    0.48
    iſen
    0.47
    Activations Density 0.584%

    No Known Activations