© 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. 7890
    Prev
    Next
    INDEX
    Explanations

    technical terms and features related to software applications and user interfaces

    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
     للاسماء
    -0.33
     zaak
    -0.33
     föl
    -0.27
     vouloir
    -0.26
    occuper
    -0.26
    pushFollow
    -0.25
    assemblée
    -0.25
     committed
    -0.25
     personne
    -0.24
    开口道
    -0.23
    POSITIVE LOGITS
     functionality
    1.47
     feature
    1.37
     option
    1.34
     mechanism
    1.26
     capability
    1.23
    功能
    1.17
     functionalities
    1.14
     기능
    1.13
    機能
    1.11
     capabilities
    1.09
    Activations Density 0.878%

    No Known Activations