© 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. 33-GEMMASCOPE-RES-16K
    6. 11923
    Prev
    Next
    INDEX
    Explanations

    references to the present state or ongoing actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/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.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     wcześniej
    -1.09
     kiedyś
    -1.01
     initially
    -1.01
     previously
    -1.00
     then
    -0.98
     ранее
    -0.98
     następnie
    -0.98
     originally
    -0.97
     inicialmente
    -0.96
     później
    -0.96
    POSITIVE LOGITS
    msgTypes
    0.59
    ThemeOverlay
    0.52
     Efq
    0.50
     thanks
    0.49
    すっかり
    0.48
     архивлан
    0.47
     ***!
    0.46
     unrecogn
    0.46
    دانشنامهٔ
    0.44
    protoimpl
    0.44
    Activations Density 0.551%

    No Known Activations