© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 10385
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions and notation related to finite root systems

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

    Superscripted "re" within mathematical expressions

    np_acts-logits-general · gemini-2.0-flash

    ${\mathcal{R}}{^\mathrm{re}}$ notation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fußballspieler
    -0.35
     çıkar
    -0.32
     cercan
    -0.32
     golfe
    -0.31
    träd
    -0.30
     endroits
    -0.30
     Jurí
    -0.30
     oportunidad
    -0.30
    ufig
    -0.29
     Gubernur
    -0.28
    POSITIVE LOGITS
     Numerade
    0.74
    ptonshire
    0.68
    stackrel
    0.66
    AnchorStyles
    0.66
     }^{
    0.63
    overset
    0.62
     dAtA
    0.62
     AssemblyCompany
    0.61
    ьаж
    0.60
     }^{(
    0.58
    Activations Density 1.375%

    No Known Activations