© 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. 101280
    Prev
    Next
    INDEX
    Explanations

    terms related to summation or aggregation

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

    sum or sums followed by various words

    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
    acade
    -0.58
    RAEL
    -0.54
     Mechan
    -0.52
    electric
    -0.50
    acamata
    -0.49
    isDirectory
    -0.48
    Mechan
    -0.47
     Italijanski
    -0.47
    bibli
    -0.47
    clientId
    -0.47
    POSITIVE LOGITS
     Sum
    1.46
    Sum
    1.38
     SUM
    1.30
     sum
    1.28
    SUM
    1.23
    sum
    1.21
     summation
    1.11
     summ
    1.09
     Sumner
    1.09
     summing
    1.09
    Activations Density 0.061%

    No Known Activations