© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 1590
    Prev
    Next
    INDEX
    Explanations

    words and phrases related to news and progress updates

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 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
    minecraftforge
    -0.67
    interceptors
    -0.61
    resizingMask
    -0.59
    WSGI
    -0.52
    ManyToMany
    -0.51
    fillType
    -0.48
    AfterViewInit
    -0.48
    ousine
    -0.48
    Pty
    -0.48
     AttributeSet
    -0.48
    POSITIVE LOGITS
     updates
    1.75
     Updates
    1.56
     update
    1.55
    updates
    1.44
    Updates
    1.39
     UPDATES
    1.32
     Update
    1.24
     updating
    1.18
     uppdater
    1.05
     actualización
    1.05
    Activations Density 0.088%

    No Known Activations