© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 26
    Prev
    Next
    INDEX
    Explanations

    instances of structured programming elements like functions, classes, and control flow statements in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    сылкі
    -0.83
    protoimpl
    -0.76
     initComponents
    -0.73
    WriteTagHelper
    -0.72
     препратки
    -0.71
    Personendaten
    -0.69
     AllMovie
    -0.69
     ویکی‌پدی
    -0.68
    jspx
    -0.68
    
    -0.68
    POSITIVE LOGITS
     nationally
    0.45
     powiet
    0.43
     while
    0.42
    毫不
    0.40
     vermelhas
    0.40
     year
    0.40
    相
    0.40
     Big
    0.39
     głó
    0.38
    mathbb
    0.38
    Activations Density 0.027%

    No Known Activations