© 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. 11-GEMMASCOPE-RES-16K
    11. 4772
    Prev
    Next
    INDEX
    Explanations

    intensifiers or qualifiers that emphasize certainty or importance

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_11/width_16k/average_l0_80
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.97
     Shades
    -0.85
    Shades
    -0.85
    Pozdrawiam
    -0.83
    stini
    -0.81
     noires
    -0.79
     Meade
    -0.77
    getCmp
    -0.77
    
    -0.77
     Wiseman
    -0.77
    POSITIVE LOGITS
     really
    1.14
     REALLY
    1.07
     realy
    1.06
    really
    0.99
     Really
    0.96
    benar
    0.89
    Really
    0.85
     quite
    0.80
    ibatis
    0.80
    ERÍA
    0.66
    Activations Density 0.051%

    No Known Activations