© 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 - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 29304
    Prev
    Next
    INDEX
    Explanations

    the word "And" as a conjunction used to connect thoughts or clauses

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

    and followed by new phrases

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     Localized
    -0.45
     locali
    -0.43
    otechnical
    -0.43
    exus
    -0.42
     Inland
    -0.42
     élé
    -0.41
     localized
    -0.41
     للاسماء
    -0.40
     Newsroom
    -0.40
    iological
    -0.40
    POSITIVE LOGITS
    And
    0.83
     And
    0.83
    그리고
    0.63
    そして
    0.57
    DockStyle
    0.56
     Và
    0.55
    Και
    0.54
     그리고
    0.53
    Și
    0.53
    Và
    0.53
    Activations Density 0.036%

    No Known Activations