© 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-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14753
    Prev
    Next
    INDEX
    Explanations

    instances of stuffing or containing items, particularly in relation to materials or substances being enclosed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
     Vikipedi
    -0.84
    ableView
    -0.59
    IndentedString
    -0.58
    MemoryWarning
    -0.52
     kapp
    -0.52
    CompleteListener
    -0.51
    љено
    -0.49
     Off
    -0.48
    pædia
    -0.48
    atru
    -0.48
    POSITIVE LOGITS
     inserted
    1.14
     inside
    1.10
    Inside
    0.94
    inside
    0.91
     Inside
    0.91
    inserted
    0.89
    Inserted
    0.88
     insertion
    0.88
     INSIDE
    0.88
     dedans
    0.87
    Activations Density 0.368%

    No Known Activations