© 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. 2-GEMMASCOPE-RES-16K
    11. 4595
    Prev
    Next
    INDEX
    Explanations

    the word "big."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CrossRef
    -0.82
     ComVisible
    -0.81
    Datuak
    -0.79
     propOrder
    -0.77
     tartalomajánló
    -0.77
    ↴
    -0.77
     invokingState
    -0.76
     kaynağından
    -0.75
    ItemBackground
    -0.75
    ]")]
    -0.74
    POSITIVE LOGITS
     big
    4.02
    big
    3.59
     BIG
    3.24
    Big
    3.13
     Big
    3.08
    BIG
    3.00
     bigger
    2.22
     huge
    2.18
     large
    2.01
     biggest
    1.98
    Activations Density 0.105%

    No Known Activations