© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 8525
    Prev
    Next
    INDEX
    Explanations

    references to specific volumes in publications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Tokens starting with "Vol" (case-insensitive)

    np_acts-logits-general · gemini-2.0-flash

    voluminous, volume, Volvocine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    EDEFAULT
    -0.56
    şak
    -0.53
    topRight
    -0.50
     contemporain
    -0.50
     animale
    -0.48
     Monfieur
    -0.48
     Barat
    -0.48
     ISTAT
    -0.47
     Privy
    -0.46
     contemporaine
    -0.46
    POSITIVE LOGITS
    
    0.70
    LookAnd
    0.67
    leys
    0.56
     CreateTagHelper
    0.54
    jsxFileName
    0.53
     useAuth
    0.52
     Pele
    0.51
     AssemblyCompany
    0.51
    Vol
    0.51
    upto
    0.51
    Activations Density 0.109%

    No Known Activations