© 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 EvalsExportsAPI 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. 5470
    Prev
    Next
    INDEX
    Explanations

    instances of character introductions and interactions

    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
    UserScript
    -0.71
    irical
    -0.61
    Архівовано
    -0.59
    stdafx
    -0.56
    reathable
    -0.55
    CDATA
    -0.53
    ujudkan
    -0.52
    anners
    -0.52
     collectivités
    -0.50
    diva
    -0.49
    POSITIVE LOGITS
     meet
    2.72
     meeting
    2.59
     met
    2.49
     Meet
    2.48
    meet
    2.39
     meets
    2.38
    Meet
    2.37
    Meeting
    2.32
     MEET
    2.23
     Meeting
    2.21
    Activations Density 0.281%

    No Known Activations