© 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. 16-GEMMASCOPE-RES-16K
    6. 13578
    Prev
    Next
    INDEX
    Explanations

    concepts related to prioritization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     museum
    -0.42
     shell
    -0.41
     vendu
    -0.40
    readFileSync
    -0.39
    FIG
    -0.39
     appunto
    -0.38
     dziewczyn
    -0.38
     //$
    -0.37
     scoprire
    -0.37
    gbaar
    -0.37
    POSITIVE LOGITS
     priority
    1.49
     Priority
    1.43
     Priorities
    1.33
     priorities
    1.30
    priority
    1.30
    Priority
    1.30
     prioriti
    1.18
    PRIORITY
    1.16
     priorité
    1.15
     prioritise
    1.13
    Activations Density 0.060%

    No Known Activations