© 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 - 65k
    9. 0-GEMMASCOPE-RES-65K
    11. 6755
    Prev
    Next
    INDEX
    Explanations

    terms that denote optimal conditions or perfect states

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    NUMX
    -0.90
     nahilalakip
    -0.83
     Efq
    -0.82
    onAttach
    -0.81
    Personendaten
    -0.79
    '},
    -0.78
     Мексичка
    -0.77
    Datuak
    -0.76
    =$?
    -0.75
     дописавши
    -0.73
    POSITIVE LOGITS
     perfect
    0.96
    Ideal
    0.88
     ideal
    0.88
    Perfect
    0.87
     Perfect
    0.86
    perfect
    0.86
     Ideal
    0.81
    ideal
    0.75
     PERFECT
    0.65
    理想
    0.65
    Activations Density 0.054%

    No Known Activations