© 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
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 3366
    Prev
    Next
    INDEX
    Explanations

    repeated usage of the Japanese particle "を" indicating direct objects

    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
     enfans
    -0.48
    évaluateur
    -0.47
     ſche
    -0.47
     ſtate
    -0.44
     habet
    -0.43
     houſe
    -0.40
     maș
    -0.40
     creș
    -0.40
     ſta
    -0.39
     indígen
    -0.39
    POSITIVE LOGITS
    を
    2.67
    를
    2.09
    을
    1.95
     を
    1.66
    りを
    1.41
    いを
    1.35
     를
    1.27
    のを
    1.25
    ことを
    1.25
    さんを
    1.16
    Activations Density 0.013%

    No Known Activations