© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 8704
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical and statistical models, particularly those involving percolation thresholds and recursion

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.70
    :✨
    -0.56
    IsContent
    -0.55
    writeFieldEnd
    -0.54
    igshid
    -0.53
    DSL
    -0.53
     typelib
    -0.53
    mbggenerated
    -0.52
     "..\..\..\
    -0.51
    agaan
    -0.50
    POSITIVE LOGITS
     المعيارى
    0.56
    InputBorder
    0.48
     lumineuse
    0.47
     rând
    0.47
     næste
    0.47
     noDo
    0.47
     initiale
    0.46
    (!__
    0.46
    ::~
    0.46
     dasselbe
    0.46
    Activations Density 1.751%

    No Known Activations