© 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. 33-GEMMASCOPE-RES-16K
    11. 11573
    Prev
    Next
    INDEX
    Explanations

    references to physical structures and barriers, especially in the context of confinement or protection

    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
     квартира
    -0.34
     ujednoznacz
    -0.33
     icônes
    -0.33
    enterOuterAlt
    -0.33
    geber
    -0.33
    rasser
    -0.33
     Crusoe
    -0.33
     Dorf
    -0.33
    ressible
    -0.32
    ➋
    -0.32
    POSITIVE LOGITS
     fence
    2.14
     fences
    2.00
     Fence
    1.81
     fencing
    1.78
    fence
    1.73
    Fence
    1.64
     gates
    1.49
     Fencing
    1.49
     barrier
    1.47
     gate
    1.45
    Activations Density 0.250%

    No Known Activations