© 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. 8-GEMMASCOPE-RES-16K
    6. 2450
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical concepts, particularly algebraic structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </em>
    -0.70
    mathrm
    -0.59
     صد
    -0.58
     won
    -0.57
    lež
    -0.55
     cacci
    -0.55
    mstyle
    -0.53
     
    -0.52
    コロ
    -0.52
    won
    -0.51
    POSITIVE LOGITS
    RenderAtEndOf
    1.21
    setVerticalGroup
    1.05
     '\\;'
    1.00
    webElementXpaths
    0.98
    GEBURTSDATUM
    0.95
     المعيارى
    0.93
     InputDecoration
    0.93
     Мексичка
    0.91
     ModelExpression
    0.90
    AndEndTag
    0.87
    Activations Density 2.122%

    No Known Activations