© 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. 746
    Prev
    Next
    INDEX
    Explanations

    symbols and notation related to mathematical expressions and formulas

    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
    es
    -0.59
    
    -0.56
    to
    -0.55
    ↵
    -0.51
    *
    -0.51
     lai
    -0.50
    .
    -0.50
    a
    -0.50
    To
    -0.48
     Wilder
    -0.48
    POSITIVE LOGITS
     كومونز
    1.08
     StringTokenizer
    0.89
     незавершена
    0.87
     يتيمه
    0.86
     ENTITY
    0.84
    oogle
    0.81
     }(\
    0.81
    Cordialement
    0.80
    Portale
    0.79
     MainAxisSize
    0.79
    Activations Density 0.515%

    No Known Activations