© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 40-GEMMASCOPE-RES-16K
    6. 1947
    Prev
    Next
    INDEX
    Explanations

    Java programming syntax and structure, particularly method definitions and system output commands

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pérd
    -0.97
     Infór
    -0.96
     desmotivaciones
    -0.94
     indígen
    -0.94
     nonUne
    -0.88
     valentín
    -0.88
     bluzka
    -0.85
     ainfi
    -0.84
    actéristi
    -0.84
     plufieurs
    -0.82
    POSITIVE LOGITS
    paramref
    0.52
    getcwd
    0.43
    scrollTop
    0.43
     dotenv
    0.42
    nativeElement
    0.41
     TextEditing
    0.41
    assertj
    0.40
    emplace
    0.40
    awt
    0.40
    ContentValues
    0.39
    Activations Density 0.358%

    No Known Activations