© 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 EvalsExportsinterp-engineNEWAPI 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. 5443
    Prev
    Next
    INDEX
    Explanations

    structured elements and organizational aspects of written documents

    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
    ulement
    -0.38
    出版年
    -0.31
     нав
    -0.28
     utafitiHapana
    -0.27
    krank
    -0.26
    ArrowToggle
    -0.26
     vạn
    -0.25
    ầy
    -0.24
    ētu
    -0.24
     fallu
    -0.23
    POSITIVE LOGITS
     ending
    2.33
     concluding
    2.08
     concludes
    2.02
     conclude
    1.98
     Ending
    1.93
     ends
    1.88
     ended
    1.87
     finishing
    1.85
    Ending
    1.84
     concluded
    1.82
    Activations Density 0.380%

    No Known Activations