© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7632
    Prev
    Next
    INDEX
    Explanations

    references to reports and research findings

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

    reports or studies

    np_acts-logits-general · gemini-2.0-flash

    official reports and studies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     getItemCount
    -0.45
    CodedInputStream
    -0.40
    fit
    -0.38
    QtWidgets
    -0.38
     postIndex
    -0.37
     voelen
    -0.36
    circuit
    -0.35
    circuits
    -0.35
    InputBorder
    -0.34
     jaula
    -0.34
    POSITIVE LOGITS
     report
    0.63
     económicos
    0.52
     commissioned
    0.52
    Наводи
    0.51
     Report
    0.50
    Report
    0.49
     reports
    0.48
    Lähteet
    0.48
     económicas
    0.48
    TableBody
    0.47
    Activations Density 0.333%

    No Known Activations