© 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. 10632
    Prev
    Next
    INDEX
    Explanations

    references to instances and instance-based programming concepts

    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
    AddTagHelper
    -0.39
    RectangleBorder
    -0.37
    Hochspringen
    -0.37
    AEL
    -0.37
    Jereo
    -0.35
    forChild
    -0.35
    getLeft
    -0.35
    ER
    -0.34
     Gelder
    -0.34
    hoea
    -0.34
    POSITIVE LOGITS
     INST
    0.69
     Inst
    0.68
     INSTANCE
    0.66
    LookAnd
    0.65
     Instance
    0.64
    inst
    0.63
    Inst
    0.63
     inst
    0.62
     getInstance
    0.61
    instan
    0.60
    Activations Density 0.124%

    No Known Activations