© 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. 15-GEMMASCOPE-RES-16K
    6. 2357
    Prev
    Next
    INDEX
    Explanations

    technical specifications and parameters related to programming or system configuration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     >=",
    -0.49
    KURZBESCHREIBUNG
    -0.49
     <>",
    -0.44
     AssemblyTitle
    -0.42
     ExecuteAsync
    -0.41
    expandindo
    -0.40
    setupUi
    -0.37
    Sheriff
    -0.37
    </tfoot>
    -0.37
    setVerticalGroup
    -0.37
    POSITIVE LOGITS
     Vikipedi
    0.44
     roja
    0.42
    DeleteBehavior
    0.42
    SaveVideo
    0.41
    findpost
    0.40
     שוליים
    0.39
    iego
    0.39
     يتيمه
    0.38
    ChrTalk
    0.36
     Vorteil
    0.36
    Activations Density 3.147%

    No Known Activations