© 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. 6017
    Prev
    Next
    INDEX
    Explanations

    punctuation and connective phrases indicative of complex sentence structures

    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
     Autorizaciones
    -0.66
     Majefty
    -0.52
    Jîn
    -0.50
     everytime
    -0.50
    NameInMap
    -0.49
    المكان
    -0.48
    原始内容存档于
    -0.48
     estekak
    -0.48
    ⤹
    -0.48
     fres
    -0.48
    POSITIVE LOGITS
    Indeed
    1.27
     Indeed
    1.25
     indeed
    1.10
    Interestingly
    1.04
    Certainly
    1.03
     Interestingly
    0.98
     Certainly
    0.96
    Ironically
    0.94
    indeed
    0.93
    Clearly
    0.93
    Activations Density 1.246%

    No Known Activations