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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 1765
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and logical operators involved in set theory and algebra

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

    Mathematical notation with intersection symbols

    np_acts-logits-general · gemini-2.0-flash

    intersection or logical AND

    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
     auszu
    -0.41
    躇
    -0.36
    StoryboardSegue
    -0.34
    enumi
    -0.33
    enumii
    -0.30
    FieldNumber
    -0.29
     pó
    -0.29
     hapa
    -0.28
    شوف
    -0.27
     woj
    -0.27
    POSITIVE LOGITS
    Intersection
    0.83
     Intersection
    0.82
     intersection
    0.81
    intersection
    0.80
     &&
    0.71
    intersect
    0.71
     فريبيس
    0.71
    dafx
    0.68
    ьаж
    0.67
    &&
    0.66
    Activations Density 0.716%

    No Known Activations