© 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. 454
    Prev
    Next
    INDEX
    Explanations

    phrases indicating progression or arrival at a point in a narrative or argument

    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
     coming
    -0.52
     COMING
    -0.49
     upcoming
    -0.45
     forthcoming
    -0.43
    Coming
    -0.41
     incoming
    -0.40
     went
    -0.40
     returning
    -0.40
     llegar
    -0.40
     return
    -0.40
    POSITIVE LOGITS
    ंदीखरीदारी
    0.73
    AndEndTag
    0.72
     NSCoder
    0.66
    ImageContext
    0.64
     bezeichneter
    0.63
    SequentialGroup
    0.62
    verwijspagina
    0.62
     initComponents
    0.60
    AndroidJUnit
    0.60
    GOTREF
    0.59
    Activations Density 0.150%

    No Known Activations