© 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. 20-GEMMASCOPE-RES-131K
    11. 66941
    Prev
    Next
    INDEX
    Explanations

    the word "besides" and its variations, indicating a focus on additional points or contrasts in discussions

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

    introducing additional points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Prayer
    -0.62
    nerability
    -0.61
    Cork
    -0.60
    aryen
    -0.59
    Burke
    -0.57
     gogh
    -0.57
     snippetHide
    -0.57
     serangga
    -0.57
     taker
    -0.57
     Packet
    -0.56
    POSITIVE LOGITS
    besides
    0.85
    Besides
    0.83
     Besides
    0.81
     besides
    0.75
    Oltre
    0.66
     BEYOND
    0.66
     Beside
    0.65
     Oltre
    0.65
    oltre
    0.61
    Neben
    0.61
    Activations Density 0.003%

    No Known Activations