© 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. 11-GEMMASCOPE-RES-16K
    11. 5224
    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 @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     aparcamiento
    -0.40
     Schick
    -0.39
     messaging
    -0.39
     debilidad
    -0.39
     Sme
    -0.38
     Mice
    -0.38
     Hag
    -0.36
     پد
    -0.36
    brainer
    -0.36
     coches
    -0.36
    POSITIVE LOGITS
     Full
    1.85
     full
    1.84
    Full
    1.83
     FULL
    1.63
    full
    1.58
    FULL
    1.53
    isFull
    1.27
     fuller
    1.23
    getFull
    1.16
     fullest
    1.11
    Activations Density 0.086%

    No Known Activations