© 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. 21-GEMMASCOPE-RES-16K
    11. 3536
    Prev
    Next
    INDEX
    Explanations

    aspects related to accomplishments and project evaluations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.75
    bibfield
    -0.67
     utafitiHapana
    -0.66
    bibinfo
    -0.65
     bezeichneter
    -0.63
    tières
    -0.62
     mxArray
    -0.61
     vong
    -0.58
     gql
    -0.57
    存于互联网档案馆
    -0.56
    POSITIVE LOGITS
     thus
    2.71
     so
    2.08
    thus
    2.03
    Thus
    1.93
     Thus
    1.85
     sejauh
    1.53
    so
    1.49
    So
    1.46
     bisher
    1.45
     così
    1.41
    Activations Density 0.482%

    No Known Activations