© 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-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 11724
    Prev
    Next
    INDEX
    Explanations

    numerical values and related expressions

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

    Numbers followed by other symbols

    np_acts-logits-general · gemini-2.0-flash

    next item in sequence

    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
    transQ
    -0.92
     zwiſchen
    -0.88
     Waſſer
    -0.88
    ########.
    -0.85
    rungsseite
    -0.85
     zuſammen
    -0.85
     queſta
    -0.84
     increí
    -0.83
     Geſch
    -0.83
     erſt
    -0.82
    POSITIVE LOGITS
     prochain
    0.30
     next
    0.29
    ModelBuilder
    0.25
     следующий
    0.25
    next
    0.25
    下一
    0.22
    more
    0.22
     стан
    0.22
     second
    0.21
     пере
    0.21
    Activations Density 2.042%

    No Known Activations