© 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. 0-GEMMASCOPE-RES-16K
    11. 2058
    Prev
    Next
    INDEX
    Explanations

    terms related to controllers and their functionalities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.52
     uſe
    -0.47
     anſ
    -0.43
     Reſ
    -0.40
     ſee
    -0.39
     viſ
    -0.38
     Anſ
    -0.38
    存于互联网档案馆
    -0.36
     leaſt
    -0.36
     незавершена
    -0.35
    POSITIVE LOGITS
     doubled
    0.74
     doubling
    0.68
    oms
    0.66
     Doubles
    0.64
     topped
    0.60
     Controller
    0.60
    insics
    0.59
    Doubles
    0.58
     controller
    0.58
     tripled
    0.57
    Activations Density 0.311%

    No Known Activations