© 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-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 14225
    Prev
    Next
    INDEX
    Explanations

    mathematical operators and notation related to mathematical functions and expressions

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

    LaTeX mathematical operators and function names in algebraic geometry.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IntoConstraints
    -0.47
     caña
    -0.38
     états
    -0.35
    makeConstraints
    -0.35
     foco
    -0.34
     fermo
    -0.34
     código
    -0.34
    verwijspagina
    -0.34
    ContentAsync
    -0.33
     "..\..\..\
    -0.33
    POSITIVE LOGITS
     nakalista
    0.59
    operatorname
    0.54
    :✨
    0.51
     виправивши
    0.51
     autorytatywna
    0.51
    MemoryWarning
    0.48
    __":
    0.47
    TintMode
    0.46
    cipar
    0.46
    thig
    0.46
    Activations Density 0.327%

    No Known Activations