© 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-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 2262
    Prev
    Next
    INDEX
    Explanations

    key programming symbols and syntax related to coding structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Code, symbols, and foreign language fragments

    np_acts-logits-general · gemini-2.0-flash

    brackets and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ագրություններ
    -0.77
    '))
    -0.68
    躇
    -0.66
    Spoljašnje
    -0.60
    '>{
    -0.58
    
    -0.58
     ujednoznacz
    -0.57
     Claw
    -0.57
     invokingState
    -0.57
    цездатний
    -0.56
    POSITIVE LOGITS
     resourceCulture
    0.64
    Erreferentziak
    0.41
     kasarigan
    0.38
     跳转至
    0.38
    Przypisy
    0.37
    .-
    0.37
    MergeFrom
    0.37
    .-.
    0.36
    _.
    0.33
    .[
    0.33
    Activations Density 0.947%

    No Known Activations