© 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. 0-GEMMASCOPE-RES-16K
    11. 64
    Prev
    Next
    INDEX
    Explanations

    code-like syntax elements, particularly backticks and brackets, used in programming or markup languages

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Bra
    -0.53
     
    -0.49
    ,
    -0.48
     Lav
    -0.47
    ...
    -0.47
     Ward
    -0.47
    .
    -0.46
     Lam
    -0.46
     plant
    -0.45
     Tem
    -0.45
    POSITIVE LOGITS
    rungsseite
    0.95
    脚注の使い方
    0.87
     `${
    0.87
     للاسماء
    0.85
    SequentialGroup
    0.82
     AssemblyTitle
    0.82
    `${
    0.81
     مشين
    0.80
     @"
    0.78
     مرئيه
    0.78
    Activations Density 0.652%

    No Known Activations