© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 77783
    Prev
    Next
    INDEX
    Explanations

    Java method signatures and related code syntax

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

    code: hex value

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Rhestr
    -0.58
    leisure
    -0.47
    MethodManager
    -0.47
     petting
    -0.47
     getItemCount
    -0.47
    ToRefresh
    -0.46
    近平
    -0.44
     Yearly
    -0.44
     Myr
    -0.44
    Vidite
    -0.44
    POSITIVE LOGITS
     code
    1.08
     Code
    0.97
    Code
    0.97
    code
    0.94
     codes
    0.89
     CODE
    0.85
     Codes
    0.84
    CODE
    0.82
     kode
    0.82
    Codes
    0.80
    Activations Density 0.076%

    No Known Activations