© 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. 13754
    Prev
    Next
    INDEX
    Explanations

    variations of the word "pal" or any related terms, indicating a focus on the concept of friendship or companionship

    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
    __':
    -1.07
    __":
    -0.85
     CGSize
    -0.82
     Sixt
    -0.78
    出版年
    -0.76
    arakhand
    -0.75
    /**
    -0.73
     Perugia
    -0.72
    ETHING
    -0.69
    resultCode
    -0.69
    POSITIVE LOGITS
     Pal
    3.18
     pal
    3.13
    Pal
    3.01
    pal
    2.77
     PAL
    2.49
    PAL
    2.33
     palettes
    1.76
     Pals
    1.66
     palate
    1.60
     Palmer
    1.60
    Activations Density 0.068%

    No Known Activations