© 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-2-2B
    7. Residual Stream - 16k
    9. 23-GEMMASCOPE-RES-16K
    11. 15000
    Prev
    Next
    INDEX
    Explanations

    references to the construction and design of buildings, particularly those made of stone

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.60
    存于互联网档案馆
    -0.58
    bonucleic
    -0.53
     confronti
    -0.53
     JScrollPane
    -0.51
     Njema
    -0.51
     Chí
    -0.50
     kaarangay
    -0.49
     bulu
    -0.48
    ophobic
    -0.48
    POSITIVE LOGITS
     stone
    1.28
     brick
    1.17
     bricks
    1.16
     stones
    1.14
     masonry
    1.09
     mortar
    1.01
     cement
    0.98
     Bricks
    0.97
     STONE
    0.97
    brick
    0.95
    Activations Density 0.166%

    No Known Activations