© 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-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 2525
    Prev
    Next
    INDEX
    Explanations

    references to comparative claims and relationships between different concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    "vice versa" and opposites

    np_acts-logits-general · gemini-2.0-flash

    vice versa

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Tikang
    -0.53
    LabelTagHelper
    -0.53
    ын
    -0.52
    providedIn
    -0.50
     capitolo
    -0.50
    stalline
    -0.49
    érienne
    -0.49
    Πηγές
    -0.49
     honom
    -0.48
    ptonshire
    -0.48
    POSITIVE LOGITS
     vice
    2.85
     viceversa
    2.04
     Vice
    2.01
     umgekehrt
    1.98
    Vice
    1.95
    vice
    1.92
     conversely
    1.80
     Conversely
    1.78
     reverse
    1.72
     vise
    1.72
    Activations Density 0.409%

    No Known Activations