© 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. 33-GEMMASCOPE-RES-16K
    11. 13989
    Prev
    Next
    INDEX
    Explanations

    references to statistical analysis methods and structures in data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AutoScale
    -0.38
     CreateTagHelper
    -0.36
     rega
    -0.32
     apor
    -0.32
    ParallelGroup
    -0.31
     faut
    -0.30
    Bull
    -0.29
     vill
    -0.29
     diamond
    -0.29
     voire
    -0.29
    POSITIVE LOGITS
     b
    1.19
     B
    1.13
     getB
    0.95
    B
    0.90
    b
    0.89
    getB
    0.87
     б
    0.81
     ب
    0.77
    ⓑ
    0.77
    ｂ
    0.68
    Activations Density 0.830%

    No Known Activations