© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 34-GEMMASCOPE-RES-16K
    11. 12155
    Prev
    Next
    INDEX
    Explanations

    words related to passenger vehicles and transportation systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 34-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_34/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.34.hook_resid_post
    Hook Layer
    34
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    存于互联网档案馆
    -0.73
    ंदीखरीदारी
    -0.72
     محفوظة
    -0.71
     pinulongan
    -0.68
    yntaxException
    -0.67
    :✨
    -0.65
     Normdatei
    -0.63
     AssemblyCulture
    -0.63
    MemoryWarning
    -0.63
    +#+#
    -0.61
    POSITIVE LOGITS
     consumer
    0.37
     sector
    0.36
     clientèle
    0.35
     }}">
    0.35
    ，”
    0.33
    イヤレス
    0.33
     senare
    0.33
     consumers
    0.32
     secteur
    0.31
     contemporaine
    0.31
    Activations Density 1.389%

    No Known Activations