© 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. 9168
    Prev
    Next
    INDEX
    Explanations

    the occurrences of the prefix or term "es."

    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
     Pantal
    -0.63
     Taller
    -0.63
    ẵn
    -0.61
     remb
    -0.60
     dring
    -0.58
    moh
    -0.58
     Wallflower
    -0.58
     Complete
    -0.57
    Ỗ
    -0.57
     Buff
    -0.57
    POSITIVE LOGITS
     Es
    2.63
     es
    2.40
    Es
    2.39
     ES
    2.29
    ES
    2.06
    es
    2.05
     Esch
    1.36
     ESC
    1.33
     Esmeralda
    1.27
     Estelle
    1.27
    Activations Density 0.058%

    No Known Activations