© 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. 3-GEMMASCOPE-RES-16K
    11. 5082
    Prev
    Next
    INDEX
    Explanations

    technical elements and components related to software or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Majefty
    -0.73
     pleaſure
    -0.67
     purpoſe
    -0.49
     ftate
    -0.46
     consultato
    -0.44
    SocketChannel
    -0.44
     fhort
    -0.44
     šķ
    -0.43
    tingu
    -0.43
    ftant
    -0.41
    POSITIVE LOGITS
    xis
    0.93
    tis
    0.90
    ilis
    0.90
     Aris
    0.89
     Manas
    0.88
    xas
    0.87
    antis
    0.87
     Solis
    0.87
    onis
    0.86
    eris
    0.86
    Activations Density 1.995%

    No Known Activations