© 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. 3-GEMMASCOPE-RES-16K
    11. 2792
    Prev
    Next
    INDEX
    Explanations

    instances of the word "fall" in various forms and contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RadioGroup
    -0.78
     Robson
    -0.71
     دیکھیے
    -0.71
     MainAxisSize
    -0.68
     команди
    -0.67
    QUOTES
    -0.64
    gebraucht
    -0.64
    ürger
    -0.62
    icolon
    -0.61
     віта
    -0.61
    POSITIVE LOGITS
     fell
    2.68
     falls
    2.68
     fall
    2.68
     falling
    2.61
    falling
    2.50
     FALL
    2.45
     Falling
    2.45
    fall
    2.44
    FALL
    2.42
     fallen
    2.41
    Activations Density 0.055%

    No Known Activations