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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 5193
    Prev
    Next
    INDEX
    Explanations

    instances of the word "in" as well as variations and related inflections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.54
    featureID
    -0.48
    IsMutable
    -0.47
     Ine
    -0.46
    YourGuide
    -0.46
    ➟
    -0.45
     XCTest
    -0.45
    igkeiten
    -0.44
    parsedMessage
    -0.44
    protoimpl
    -0.44
    POSITIVE LOGITS
    in
    2.41
    IN
    1.32
    ins
    1.02
    inin
    0.96
    nin
    0.79
    inb
    0.75
    İN
    0.73
    tin
    0.73
    ın
    0.72
    ín
    0.71
    Activations Density 0.760%

    No Known Activations