© 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. 8677
    Prev
    Next
    INDEX
    Explanations

    references to database management systems and their components

    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
     afin
    -0.33
     amid
    -0.33
     statt
    -0.31
    ↵
    -0.30
     чтобы
    -0.29
     evitando
    -0.28
     क्योंकि
    -0.28
     irrelevant
    -0.27
     чтоб
    -0.27
     after
    -0.27
    POSITIVE LOGITS
     has
    1.22
     possesses
    1.02
     contains
    1.00
    AddTagHelper
    0.99
     seems
    0.98
     provides
    0.98
     enjoys
    0.95
     does
    0.94
     tends
    0.94
     represents
    0.91
    Activations Density 2.988%

    No Known Activations