© 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. 2-GEMMASCOPE-RES-16K
    6. 9292
    Prev
    Next
    INDEX
    Explanations

    references to web pages and pagination

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     marinho
    -0.61
    ThroughAttribute
    -0.52
    AccessorTable
    -0.52
    SharedCtor
    -0.52
    BorderFactory
    -0.50
    󠁮
    -0.49
     LoggerFactory
    -0.48
    RectangleBorder
    -0.48
    tiss
    -0.45
    tiérrez
    -0.44
    POSITIVE LOGITS
    Page
    1.12
    PAGE
    0.56
     Page
    0.56
    page
    0.53
    clearpage
    0.47
     UnityEngine
    0.43
    Fax
    0.43
    Screen
    0.42
     للمعارف
    0.41
     juvenile
    0.41
    Activations Density 0.214%

    No Known Activations