© 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. 300
    Prev
    Next
    INDEX
    Explanations

    names of characters and people, particularly in a narrative or story context

    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
     fuoco
    -0.39
    Predecesor
    -0.37
     iVar
    -0.36
     büy
    -0.36
    createObject
    -0.35
    penup
    -0.34
     прока
    -0.33
     PopupWindow
    -0.32
     bouwen
    -0.32
    impanan
    -0.31
    POSITIVE LOGITS
    OGND
    0.65
    Rüyada
    0.55
    kulu
    0.54
    dob
    0.53
    agoza
    0.53
    nolia
    0.52
    Pran
    0.52
     Jovi
    0.51
     виправивши
    0.51
    éster
    0.51
    Activations Density 1.375%

    No Known Activations