© 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
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 11114
    Prev
    Next
    INDEX
    Explanations

    phrases indicating completeness or fullness

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ocasião
    -0.48
     conductores
    -0.48
     Städte
    -0.48
     debilidad
    -0.48
     זאת
    -0.45
     Mice
    -0.44
     Schick
    -0.44
    Mice
    -0.44
     agradecimiento
    -0.42
    cody
    -0.42
    POSITIVE LOGITS
     Full
    1.29
    Full
    1.28
     full
    1.21
     FULL
    1.13
    FULL
    1.06
    full
    1.03
    isFull
    0.98
    getFull
    0.88
     fuller
    0.87
     fullName
    0.84
    Activations Density 0.048%

    No Known Activations