© 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. 3-GEMMASCOPE-RES-16K
    11. 6916
    Prev
    Next
    INDEX
    Explanations

    specific coding or programming terminology related to data structures and definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.47
    complexContent
    -0.38
    Baum
    -0.37
    bitField
    -0.37
    Pant
    -0.37
    JTextArea
    -0.36
    Портал
    -0.36
     Pant
    -0.35
    Courage
    -0.35
    Castell
    -0.35
    POSITIVE LOGITS
    rd
    3.30
     rd
    2.31
    RD
    2.25
     RD
    1.98
    rds
    1.83
    Rd
    1.73
     Rd
    1.51
    rdo
    1.11
    rdr
    1.09
    ird
    1.05
    Activations Density 0.113%

    No Known Activations