© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 10784
    Prev
    Next
    INDEX
    Explanations

    coding syntax and programming language constructs

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

    Code-related terms

    np_acts-logits-general · gemini-2.0-flash

    code tokens and structures

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/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.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſta
    -0.52
     betweenstory
    -0.48
     disambiguazione
    -0.48
     ſte
    -0.48
    ValueStyle
    -0.47
     faſt
    -0.47
    ſelves
    -0.46
     deſt
    -0.45
    ſelf
    -0.44
     Majefty
    -0.44
    POSITIVE LOGITS
    CppMethod
    0.50
    RegressionTest
    0.47
     jadx
    0.45
    GEBURTSDATUM
    0.42
    Rhestr
    0.42
    Referencies
    0.38
     dAtA
    0.37
     iVar
    0.36
     informée
    0.35
     uLocal
    0.35
    Activations Density 0.036%

    No Known Activations