© 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. 1827
    Prev
    Next
    INDEX
    Explanations

    phrases that express conjunctions or connections between ideas

    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
     createState
    -0.34
    BagConstraints
    -0.32
    IndentedString
    -0.32
     Roskov
    -0.32
    HtmlAttribute
    -0.32
    TintMode
    -0.31
     Glanz
    -0.31
     затем
    -0.30
     himself
    -0.30
    ItemBackground
    -0.30
    POSITIVE LOGITS
     extremely
    1.03
    extremely
    1.02
     extremamente
    0.92
     highly
    0.92
     estremamente
    0.91
    highly
    0.90
     very
    0.88
     extremadamente
    0.88
    Extremely
    0.87
     bersifat
    0.87
    Activations Density 0.562%

    No Known Activations