© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 65k
    5. 0-GEMMASCOPE-RES-65K
    6. 9777
    Prev
    Next
    INDEX
    Explanations

    terms related to software and technology

    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
     A
    -0.54
     C
    -0.53
     F
    -0.52
     end
    -0.50
     T
    -0.50
     Har
    -0.49
     law
    -0.49
     Is
    -0.49
     Ty
    -0.48
     i
    -0.48
    POSITIVE LOGITS
    Datuak
    1.16
     autorytatywna
    1.12
     Flas
    0.86
    ècie
    0.84
    حوالہ
    0.84
    تقاوى
    0.81
    IContainer
    0.80
     flas
    0.80
     Савезне
    0.79
     flutes
    0.78
    Activations Density 0.060%

    No Known Activations