© 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. 20-GEMMASCOPE-RES-16K
    6. 8605
    Prev
    Next
    INDEX
    Explanations

    metadata and structural elements related to programming and software documentation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     look
    -0.42
     high
    -0.40
     task
    -0.38
     taches
    -0.35
     new
    -0.35
     do
    -0.35
     coming
    -0.35
     acting
    -0.35
     used
    -0.34
     with
    -0.34
    POSITIVE LOGITS
    uxxxx
    2.64
     autorytatywna
    2.14
    GEBURTSDATUM
    2.11
    StructEnd
    2.03
     Италијани
    2.02
    Personendaten
    2.00
     noDo
    1.95
     CreateTagHelper
    1.93
    webElementXpaths
    1.92
     kaarangay
    1.91
    Activations Density 0.024%

    No Known Activations