© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2621
    Prev
    Next
    INDEX
    Explanations

    technical issues or problems related to programming

    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
     ब्रेकडाउन
    -0.55
    помним
    -0.52
    extAlignment
    -0.49
    StructEnd
    -0.46
    Personendaten
    -0.44
    fromnode
    -0.43
    weightedMode
    -0.43
    [:,:,
    -0.41
    EndInit
    -0.40
     disambiguazione
    -0.39
    POSITIVE LOGITS
     tôi
    1.78
     myself
    1.75
     saya
    1.73
     mijn
    1.47
     나는
    1.45
     я
    1.43
     minha
    1.40
     my
    1.38
    ผม
    1.35
     Tôi
    1.34
    Activations Density 0.127%

    No Known Activations