© 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. 33-GEMMASCOPE-RES-16K
    11. 11280
    Prev
    Next
    INDEX
    Explanations

    phrases related to provincial governance and environmental policy

    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
    interopRequire
    -0.64
     civilisation
    -0.61
    AddTagHelper
    -0.59
    favourite
    -0.59
     specialise
    -0.56
     colour
    -0.56
     initialise
    -0.55
    Whilst
    -0.55
    initialise
    -0.54
     specialising
    -0.54
    POSITIVE LOGITS
     otomatig
    0.45
    llavero
    0.45
     Vrbo
    0.44
     federal
    0.41
     ști
    0.40
     puteți
    0.40
    QUOTES
    0.39
    CPtr
    0.38
     Harper
    0.37
    テンツ
    0.37
    Activations Density 0.072%

    No Known Activations