© 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. 7700
    Prev
    Next
    INDEX
    Explanations

    references to measurements of weight and related scientific terminologies

    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
     scoperto
    -0.56
     málo
    -0.54
     Schon
    -0.53
     récents
    -0.53
    feld
    -0.51
    baud
    -0.51
     particolari
    -0.50
     relevantes
    -0.48
    auri
    -0.47
     paso
    -0.47
    POSITIVE LOGITS
     weight
    1.95
     weights
    1.73
     weighs
    1.62
     WEIGHT
    1.57
     Weight
    1.57
     weighed
    1.56
     weigh
    1.49
    Weight
    1.45
    weight
    1.44
     poids
    1.38
    Activations Density 0.044%

    No Known Activations