© 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. 7841
    Prev
    Next
    INDEX
    Explanations

    the mention of specific locations or entities associated with them

    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
     vVar
    -0.66
    Rüyada
    -0.66
     requestCode
    -0.59
     peace
    -0.59
     projective
    -0.57
     episodi
    -0.57
    karz
    -0.56
    peace
    -0.56
     Dice
    -0.54
     kvinna
    -0.54
    POSITIVE LOGITS
     vibr
    0.82
     filtered
    0.75
     filter
    0.75
     filtering
    0.72
     CreateTagHelper
    0.69
     vibrate
    0.68
     ویکی‌آمباردا
    0.68
     filt
    0.67
     THR
    0.67
     Filtering
    0.65
    Activations Density 0.047%

    No Known Activations