© 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. 12-GEMMASCOPE-RES-16K
    11. 8478
    Prev
    Next
    INDEX
    Explanations

    referencing words that indicate comparison or specification between subjects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Frie
    -0.41
    جمعیت
    -0.40
    Kanpo
    -0.40
    walks
    -0.37
    Walk
    -0.36
    nouvelle
    -0.35
    crowd
    -0.35
    walk
    -0.34
    fountain
    -0.34
    surface
    -0.33
    POSITIVE LOGITS
     respectively
    1.44
    respectively
    1.19
     respectivamente
    1.16
     respectivement
    1.12
     respective
    1.05
     соответственно
    0.83
    それぞれ
    0.83
    分别
    0.82
     rispet
    0.81
    分別
    0.81
    Activations Density 0.249%

    No Known Activations