© 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-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3553
    Prev
    Next
    INDEX
    Explanations

    instances of the substring "Che" followed by any sequence, particularly looking for references in a scientific or scholarly context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 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
    ussch
    -0.37
     disponibilités
    -0.36
    ufnahme
    -0.33
    Rüyada
    -0.33
     potuto
    -0.31
    labus
    -0.31
     Christina
    -0.30
    /**
    -0.30
     Berne
    -0.30
     PopupWindow
    -0.29
    POSITIVE LOGITS
     Che
    3.59
    Che
    3.42
     che
    3.09
     CHE
    2.98
    che
    2.98
    CHE
    2.72
     chemo
    2.16
     cheats
    2.03
     Chet
    1.98
     cheating
    1.95
    Activations Density 0.872%

    No Known Activations